Deep Learning with Differential Privacy
arXiv:1607.00133 · doi:10.1145/2976749.2978318
Abstract
Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information. The models should not expose private information in these datasets. Addressing this goal, we develop new algorithmic techniques for learning and a refined analysis of privacy costs within the framework of differential privacy. Our implementation and experiments demonstrate that we can train deep neural networks with non-convex objectives, under a modest privacy budget, and at a manageable cost in software complexity, training efficiency, and model quality.
References in corpus (12)
- Efficient Estimation of Word Representations in Vector Space
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Deep Learning with Differential Privacy
- Renyi Differential Privacy
- Differentially Private Empirical Risk Minimization
- Grammar as a Foreign Language
- Fractional Max-Pooling
- Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity
- Move Evaluation in Go Using Deep Convolutional Neural Networks
- Privacy Odometers and Filters: Pay-as-you-Go Composition
- Efficient Per-Example Gradient Computations
- Large Scale Kernel Learning using Block Coordinate Descent
Cited by in corpus (926)
- Deep Learning with Differential Privacy
- The Future of Digital Health with Federated Learning
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
- A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
- Renyi Differential Privacy
- A Survey on Distributed Machine Learning
- Deep learning for cardiac image segmentation: A review
- How To Backdoor Federated Learning
- Federated Machine Learning: Concept and Applications
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Deep Reinforcement Learning: An Overview
- Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryption
- Can You Really Backdoor Federated Learning?
- From Distributed Machine Learning to Federated Learning: A Survey
- Technical Privacy Metrics: a Systematic Survey
- Differentially Private Generative Adversarial Network
- HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning
- GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
- Prochlo: Strong Privacy for Analytics in the Crowd
- Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
- Mobile Sensor Data Anonymization
- Extracting Training Data from Large Language Models
- Protection Against Reconstruction and Its Applications in Private Federated Learning
- Local Differential Privacy for Deep Learning
- Threats to Federated Learning: A Survey
- A Survey of Privacy Attacks in Machine Learning
- Adversarial Examples: Attacks and Defenses for Deep Learning
- Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
- Federated Learning with Bayesian Differential Privacy
- Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
- Differentially Private Model Publishing for Deep Learning
- Practical Secure Aggregation for Federated Learning on User-Held Data
- DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments
- DP-ADMM: ADMM-based Distributed Learning with Differential Privacy
- Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
- More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence
- Privacy Risks of Securing Machine Learning Models against Adversarial Examples
- SecureBoost: A Lossless Federated Learning Framework
- Fast Yet Effective Machine Unlearning
- Differential Privacy-enabled Federated Learning for Sensitive Health Data
- I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators
- Split learning for health: Distributed deep learning without sharing raw patient data
- A Field Guide to Federated Optimization
- Decentralized Federated Learning: A Survey on Security and Privacy
- A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics
- Understanding Membership Inferences on Well-Generalized Learning Models
- Decentralized Federated Learning through Proxy Model Sharing
- Privacy Preserving Face Recognition Utilizing Differential Privacy
- How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
- Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy
- Differentially Private Synthetic Medical Data Generation using Convolutional GANs
- Federated Learning in Mobile Edge Networks: A Comprehensive Survey
- Privacy-preserving Federated Learning for Residential Short Term Load Forecasting
- Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
- Jury Learning: Integrating Dissenting Voices into Machine Learning Models
- Do Gradient Inversion Attacks Make Federated Learning Unsafe?
- SinGAN-Seg: Synthetic training data generation for medical image segmentation
- Edge Intelligence: Architectures, Challenges, and Applications
- Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey
- Quantum federated learning through blind quantum computing
- GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learning
- Privacy Amplification by Iteration
- Privacy-Preserving Deep Learning via Weight Transmission
- IBM Federated Learning: an Enterprise Framework White Paper V0.1
- Abnormal Client Behavior Detection in Federated Learning
- Trustworthy Graph Neural Networks: Aspects, Methods and Trends
- Privacy-preserving Artificial Intelligence Techniques in Biomedicine
- FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumonia
- Deep Learning Methods for Fingerprint-Based Indoor Positioning: A Review
- A Review of Anonymization for Healthcare Data
- Gaussian Differential Privacy
- From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security
- Correlated Differential Privacy: Feature Selection in Machine Learning
- A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysis
- Thieves on Sesame Street! Model Extraction of BERT-based APIs
- Privacy in Deep Learning: A Survey
- A Platform-Free Proof of Federated Learning Consensus Mechanism for Sustainable Blockchains
- Label-Only Membership Inference Attacks
- When Machine Learning Meets Privacy: A Survey and Outlook
- Quantifying Privacy Leakage in Graph Embedding
- Preserving Privacy and Security in Federated Learning
- Over-the-Air Computation for 6G: Foundations, Technologies, and Applications
- Domain Generalization for Medical Image Analysis: A Review
- Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer
- Practical Blind Membership Inference Attack via Differential Comparisons
- Analyzing Information Leakage of Updates to Natural Language Models
- Unsolved Problems in ML Safety
- VAFL: a Method of Vertical Asynchronous Federated Learning
- Federated Learning with Differential Privacy: Algorithms and Performance Analysis
- Rényi Differential Privacy of the Sampled Gaussian Mechanism
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
- A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning
- PPGAN: Privacy-preserving Generative Adversarial Network
- Differentially Private Learning with Adaptive Clipping
- Systematic Evaluation of Privacy Risks of Machine Learning Models
- Evaluating Differentially Private Machine Learning in Practice
- Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses
- Federated Deep Reinforcement Learning
- Trustworthy AI: Securing Sensitive Data in Large Language Models
- Data Minimization for GDPR Compliance in Machine Learning Models
- Private Stochastic Convex Optimization with Optimal Rates
- Privacy-Preserving Machine Learning: Methods, Challenges and Directions
- Differential Privacy Has Disparate Impact on Model Accuracy
- Artificial Intelligence of Things: A Survey
- Efficient Deep Learning on Multi-Source Private Data
- A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
- Large Language Models Can Be Strong Differentially Private Learners
- A Hybrid Approach to Privacy-Preserving Federated Learning
- Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
- Free-riders in Federated Learning: Attacks and Defenses
- On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
- Making AI Forget You: Data Deletion in Machine Learning
- Leveraging Generative AI Models for Synthetic Data Generation in Healthcare: Balancing Research and Privacy
- Salvaging Federated Learning by Local Adaptation
- Federated Learning for Healthcare Informatics
- An Efficient and Scalable Privacy Preserving Algorithm for Big Data and Data Streams
- A Survey of Privacy Vulnerabilities of Mobile Device Sensors
- A Study of Face Obfuscation in ImageNet
- Scalable and Differentially Private Distributed Aggregation in the Shuffled Model
- Local Differential Privacy and Its Applications: A Comprehensive Survey
- Differentially Private Learning Needs Better Features (or Much More Data)
- Label Leakage and Protection in Two-party Split Learning
- Differential Privacy for Eye-Tracking Data
- Membership Inference Attacks and Defenses in Classification Models
- Privacy-preserving Federated Brain Tumour Segmentation
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks
- CrypTen: Secure Multi-Party Computation Meets Machine Learning
- AdaCliP: Adaptive Clipping for Private SGD
- Understanding Gradient Clipping in Private SGD: A Geometric Perspective
- Security and Privacy Issues in Deep Learning
- On Lightweight Privacy-Preserving Collaborative Learning for IoT Objects
- Private Federated Learning with Domain Adaptation
- Artificial Intelligence in Glioma Imaging: Challenges and Advances
- Privately Fine-Tuning Large Language Models with Differential Privacy
- BlindFL: Vertical Federated Machine Learning without Peeking into Your Data
- The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
- Comparative Study of Differentially Private Data Synthesis Methods
- Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
- Learning Anonymized Representations with Adversarial Neural Networks
- A Simple Differentiable Programming Language
- Advances in Robust Federated Learning: A Survey with Heterogeneity Considerations
- A Safety Framework for Critical Systems Utilising Deep Neural Networks
- Throughput-Optimal Topology Design for Cross-Silo Federated Learning
- Defending Model Inversion and Membership Inference Attacks via Prediction Purification
- A blockchain-orchestrated Federated Learning architecture for healthcare consortia
- ScaleSFL: A Sharding Solution for Blockchain-Based Federated Learning
- FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systems
- Communication-Computation Efficient Secure Aggregation for Federated Learning
- DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass
- Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
- Oort: Efficient Federated Learning via Guided Participant Selection
- The Cost of Privacy: Rates of Convergence for Parameter Estimation with Differential Privacy
- DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
- RAB: Provable Robustness Against Backdoor Attacks
- Differentially Private Fine-tuning of Language Models
- ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
- Generative adversarial networks in time series: A survey and taxonomy
- The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
- Unlearnable Examples: Making Personal Data Unexploitable
- Towards Communication-efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things
- Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey
- AutoGAN-based Dimension Reduction for Privacy Preservation
- Privacy-preserving parametric inference: a case for robust statistics
- Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
- Privacy and Trust Redefined in Federated Machine Learning
- Natural Language Understanding with Privacy-Preserving BERT
- Dopamine: Differentially Private Federated Learning on Medical Data
- Generative Models for Effective ML on Private, Decentralized Datasets
- Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
- Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging
- Semi-Synchronous Federated Learning for Energy-Efficient Training and Accelerated Convergence in Cross-Silo Settings
- FederBoost: Private Federated Learning for GBDT
- SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregation
- Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
- Federated Learning with Only Positive Labels
- Secure Byzantine-Robust Machine Learning
- Differentially Private Graph Classification with GNNs
- Challenges of Privacy-Preserving Machine Learning in IoT
- On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches
- Federated Learning for Ranking Browser History Suggestions
- Generative Models for Synthetic Urban Mobility Data: A Systematic Literature Review
- The Skellam Mechanism for Differentially Private Federated Learning
- Exploring Design and Governance Challenges in the Development of Privacy-Preserving Computation
- secureTF: A Secure TensorFlow Framework
- Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform
- Computing Local Sensitivities of Counting Queries with Joins
- Privacy Management and Optimal Pricing in People-Centric Sensing
- Federated Learning with Buffered Asynchronous Aggregation
- Privacy Adversarial Network: Representation Learning for Mobile Data Privacy
- Towards Probabilistic Verification of Machine Unlearning
- Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
- Generating Artificial Data for Private Deep Learning
- The Discrete Gaussian for Differential Privacy
- User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition in Federated Learning
- A Federated Deep Learning Framework for Privacy Preservation and Communication Efficiency
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
- Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation
- The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
- Federated Boosted Decision Trees with Differential Privacy
- Fed-Focal Loss for imbalanced data classification in Federated Learning
- Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates
- Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning
- Similarity-based Label Inference Attack against Training and Inference of Split Learning
- Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs
- Health Data in an Open World
- Radioactive data: tracing through training
- Adversarial Examples Make Strong Poisons
- Gradient Centralization: A New Optimization Technique for Deep Neural Networks
- Stochastic, Distributed and Federated Optimization for Machine Learning
- Learning Privately over Distributed Features: An ADMM Sharing Approach
- Coded Machine Unlearning
- Machine Learning Models that Remember Too Much
- Differentially Private Data Generative Models
- How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning
- Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey
- Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)
- GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
- A Customized Text Sanitization Mechanism with Differential Privacy
- Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning
- GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions
- Pointwise Maximal Leakage
- Synthesis of Realistic ECG using Generative Adversarial Networks
- Improving the utility of locally differentially private protocols for longitudinal and multidimensional frequency estimates
- FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction
- Leakage of Dataset Properties in Multi-Party Machine Learning
- LinkedIn's Audience Engagements API: A Privacy Preserving Data Analytics System at Scale
- Learning Adversary-Resistant Deep Neural Networks
- HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
- Secure Federated Submodel Learning
- Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
- Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
- Practical Vertical Federated Learning with Unsupervised Representation Learning
- Forecasting: theory and practice
- Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
- Successive Point-of-Interest Recommendation with Local Differential Privacy
- Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning
- Asynchronous Federated Learning with Differential Privacy for Edge Intelligence
- Privado: Practical and Secure DNN Inference with Enclaves
- Privacy-preserving machine learning for healthcare: open challenges and future perspectives
- Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
- Differentially Private Federated Clustering over Non-IID Data
- Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems
- Practical Defences Against Model Inversion Attacks for Split Neural Networks
- Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
- Personalized Federated Learning with First Order Model Optimization
- Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
- Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries
- Differentially-Private "Draw and Discard" Machine Learning
- Random Sampling Plus Fake Data: Multidimensional Frequency Estimates With Local Differential Privacy
- GAMIN: An Adversarial Approach to Black-Box Model Inversion
- Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
- Distributed Training of Graph Convolutional Networks
- Hypothesis Testing Interpretations and Renyi Differential Privacy
- Guidelines for Implementing and Auditing Differentially Private Systems
- Differentially Private Synthetic Data: Applied Evaluations and Enhancements
- Differentially Private Federated Learning on Heterogeneous Data
- LDP-Fed: Federated Learning with Local Differential Privacy
- Approximate Span Liftings
- DP-BART for Privatized Text Rewriting under Local Differential Privacy
- DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy
- Social-Aware Clustered Federated Learning with Customized Privacy Preservation
- Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment
- A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
- Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-Coded Credentials
- The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
- Locally Differentially Private Heavy Hitter Identification
- Effectiveness of Distillation Attack and Countermeasure on Neural Network Watermarking
- Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices
- Federated Reconstruction: Partially Local Federated Learning
- Differential Privacy in Natural Language Processing: The Story So Far
- Privacy Meets Explainability: A Comprehensive Impact Benchmark
- Privacy-Preserving Ensemble Infused Enhanced Deep Neural Network Framework for Edge Cloud Convergence
- Reversible Privacy Preservation using Multi-level Encryption and Compressive Sensing
- Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
- DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation
- Enhancing the Privacy of Federated Learning with Sketching
- Opacus: User-Friendly Differential Privacy Library in PyTorch
- Poisoning the Unlabeled Dataset of Semi-Supervised Learning
- Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
- Differentially private cross-silo federated learning
- Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising
- Recent advances in deep learning theory
- VFL: A Verifiable Federated Learning with Privacy-Preserving for Big Data in Industrial IoT
- Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
- Hybrid Differentially Private Federated Learning on Vertically Partitioned Data
- Practical and Private (Deep) Learning without Sampling or Shuffling
- Personality testing of Large Language Models: Limited temporal stability, but highlighted prosociality
- Training Data Leakage Analysis in Language Models
- Privacy-preserving quantum federated learning via gradient hiding
- A Survey on Privacy-Preserving Caching at Network Edge: Classification, Solutions, and Challenges
- Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications
- Edge-cloud Collaborative Learning with Federated and Centralized Features
- Differentially Private Empirical Risk Minimization Revisited: Faster and More General
- Practical Differentially Private and Byzantine-resilient Federated Learning
- Individual Privacy Accounting via a Renyi Filter
- Greedy Shapley Client Selection for Communication-Efficient Federated Learning
- Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification
- Membership Inference Attack Susceptibility of Clinical Language Models
- Certified Data Removal from Machine Learning Models
- Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization
- Cloud2Edge Elastic AI Framework for Prototyping and Deployment of AI Inference Engines in Autonomous Vehicles
- Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms
- Private Model Compression via Knowledge Distillation
- Handcrafted Backdoors in Deep Neural Networks
- Differentially Private Vertical Federated Clustering
- Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity
- DP-LSTM: Differential Privacy-inspired LSTM for Stock Prediction Using Financial News
- Explainable Differential Privacy-Hyperdimensional Computing for Balancing Privacy and Transparency in Additive Manufacturing Monitoring
- Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications
- InstaHide: Instance-hiding Schemes for Private Distributed Learning
- Reviewing and Improving the Gaussian Mechanism for Differential Privacy
- A Differentially Private Framework for Deep Learning with Convexified Loss Functions
- Is Your Model Sensitive? SPeDaC: A New Benchmark for Detecting and Classifying Sensitive Personal Data
- Differentially Private Federated Learning for Resource-Constrained Internet of Things
- Federated Learning of N-gram Language Models
- SPEED: Secure, PrivatE, and Efficient Deep learning
- Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
- DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM
- Predominant Aspects on Security for Quantum Machine Learning: Literature Review
- The Impact of Speech Anonymization on Pathology and Its Limits
- Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization
- Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning
- Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
- Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning
- DEEProtect: Enabling Inference-based Access Control on Mobile Sensing Applications
- DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
- Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise
- Pain-Free Random Differential Privacy with Sensitivity Sampling
- Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase
- On Safeguarding Privacy and Security in the Framework of Federated Learning
- Differential Privacy for Government Agencies -- Are We There Yet?
- Self-supervised Cross-silo Federated Neural Architecture Search
- Robust Distributed Optimization With Randomly Corrupted Gradients
- Knowledge Cross-Distillation for Membership Privacy
- A Federated Multi-View Deep Learning Framework for Privacy-Preserving Recommendations
- Training Production Language Models without Memorizing User Data
- Differentially Private Federated Learning for Cancer Prediction
- Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings
- Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection
- Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy
- Anonymizing Machine Learning Models
- PPaaS: Privacy Preservation as a Service
- Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection
- Assessing differentially private deep learning with Membership Inference
- COVID-19 Imaging Data Privacy by Federated Learning Design: A Theoretical Framework
- That which we call private
- Differentially Private Generative Adversarial Networks with Model Inversion
- Mechanism Design for Multi-Party Machine Learning
- Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
- Fast-adapting and Privacy-preserving Federated Recommender System
- CAFE: Catastrophic Data Leakage in Vertical Federated Learning
- Membership Leakage in Label-Only Exposures
- Privacy-Preserving Individual-Level COVID-19 Infection Prediction via Federated Graph Learning
- A Theoretical Perspective on Differentially Private Federated Multi-task Learning
- An Overview of Privacy in Machine Learning
- Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification
- Investigating the Significance of the Bellwether Effect to Improve Software Effort Prediction: Further Empirical Study
- Differentially Private Accelerated Optimization Algorithms
- Large Scale Private Learning via Low-rank Reparametrization
- SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability
- Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
- Dordis: Efficient Federated Learning with Dropout-Resilient Differential Privacy
- DarKnight: A Data Privacy Scheme for Training and Inference of Deep Neural Networks
- How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning
- Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry
- Detecting Violations of Differential Privacy for Quantum Algorithms
- TransMIA: Membership Inference Attacks Using Transfer Shadow Training
- Membership Inference on Word Embedding and Beyond
- Characterizing and Optimizing End-to-End Systems for Private Inference
- CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU
- A Survey of AI-Related Cyber Security Risks and Countermeasures in Mobility-as-a-Service
- Better accuracy with quantified privacy: representations learned via reconstructive adversarial network
- Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
- Bounding Information Leakage in Machine Learning
- Understanding Compressive Adversarial Privacy
- Propose, Test, Release: Differentially private estimation with high probability
- A Privacy-Preserving Federated Framework with Hybrid Quantum-Enhanced Learning for Financial Fraud Detection
- Optimal Accounting of Differential Privacy via Characteristic Function
- Layer-wise Characterization of Latent Information Leakage in Federated Learning
- Private Learning on Networks: Part II
- Robust and Differentially Private Mean Estimation
- Optimal query complexity for private sequential learning against eavesdropping
- User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization
- Helen: Maliciously Secure Coopetitive Learning for Linear Models
- Privacy for All: Demystify Vulnerability Disparity of Differential Privacy against Membership Inference Attack
- RDP-GAN: A Rényi-Differential Privacy based Generative Adversarial Network
- Information Leakage in Embedding Models
- FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training
- Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning
- A Comprehensive Analysis of Information Leakage in Deep Transfer Learning
- Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent Agents
- Aggregation and Transformation of Vector-Valued Messages in the Shuffle Model of Differential Privacy
- LOGAN: Membership Inference Attacks Against Generative Models
- Group privacy for personalized federated learning
- The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Bounds
- On the Impact of Device and Behavioral Heterogeneity in Federated Learning
- Network Shuffling: Privacy Amplification via Random Walks
- Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applications
- Private Post-GAN Boosting
- Efficient Cybersecurity Assessment Using SVM and Fuzzy Evidential Reasoning for Resilient Infrastructure
- privGAN: Protecting GANs from membership inference attacks at low cost
- Differentially Private False Discovery Rate Control
- FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions
- MOBIUS: Model-Oblivious Binarized Neural Networks
- MixNN: Protection of Federated Learning Against Inference Attacks by Mixing Neural Network Layers
- Representation Transfer for Differentially Private Drug Sensitivity Prediction
- PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning
- Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs
- Computing Tight Differential Privacy Guarantees Using FFT
- SoK: Machine Learning Governance
- Differentially Private Publication of Location Entropy
- Is Private Learning Possible with Instance Encoding?
- Private Learning on Networks
- Efficient Privacy-Preserving Stochastic Nonconvex Optimization
- Towards Security Threats of Deep Learning Systems: A Survey
- Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond
- Privacy-Preserving Distributed Expectation Maximization for Gaussian Mixture Model using Subspace Perturbation
- On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
- Key Protected Classification for Collaborative Learning
- Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?
- Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics
- Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack
- Instance-optimal Mean Estimation Under Differential Privacy
- From Federated Learning to Federated Neural Architecture Search: A Survey
- SoK: Dataset Copyright Auditing in Machine Learning Systems
- Pufferfish Privacy: An Information-Theoretic Study
- Input Perturbation: A New Paradigm between Central and Local Differential Privacy
- Learning Rate Adaptation for Federated and Differentially Private Learning
- NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets
- Defending against Reconstruction Attack in Vertical Federated Learning
- Quantum-machine-assisted Drug Discovery
- Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation
- Improved Analysis of Clipping Algorithms for Non-convex Optimization
- Blockchain-Based Federated Learning in Mobile Edge Networks with Application in Internet of Vehicles
- Image Obfuscation for Privacy-Preserving Machine Learning
- Differentially Private Federated Learning with Laplacian Smoothing
- The More, the Better? A Study on Collaborative Machine Learning for DGA Detection
- DistFL: Distribution-aware Federated Learning for Mobile Scenarios
- Secure Linear Aggregation Using Decentralized Threshold Additive Homomorphic Encryption For Federated Learning
- Benchmarking Secure Sampling Protocols for Differential Privacy
- CryptoNN: Training Neural Networks over Encrypted Data
- Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget
- Anonymizing Data for Privacy-Preserving Federated Learning
- Element Level Differential Privacy: The Right Granularity of Privacy
- Bayesian Differential Privacy for Machine Learning
- Stochastic Channel-Based Federated Learning for Medical Data Privacy Preserving
- A General Framework for Data-Use Auditing of ML Models
- Weighted Distributed Differential Privacy ERM: Convex and Non-convex
- Toward an Automated Auction Framework for Wireless Federated Learning Services Market
- Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraints
- Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data
- Arbitrary Decisions are a Hidden Cost of Differentially Private Training
- CaPC Learning: Confidential and Private Collaborative Learning
- Federated -Differential Privacy
- Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings
- Privacy-Preserving Models for Legal Natural Language Processing
- Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy
- DTGAN: Differential Private Training for Tabular GANs
- Wide Network Learning with Differential Privacy
- Kamino: Constraint-Aware Differentially Private Data Synthesis
- Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
- Advances in Differential Privacy and Differentially Private Machine Learning
- Generation of Differentially Private Heterogeneous Electronic Health Records
- UniHENN: Designing Faster and More Versatile Homomorphic Encryption-based CNNs without im2col
- Federated Learning in Mobile Edge Computing: An Edge-Learning Perspective for Beyond 5G
- Privacy-preserving Non-negative Matrix Factorization with Outliers
- KiNETGAN: Enabling Distributed Network Intrusion Detection through Knowledge-Infused Synthetic Data Generation
- A(DP)SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy
- Fast and Memory Efficient Differentially Private-SGD via JL Projections
- Private Collaborative Edge Inference via Over-the-Air Computation
- Optimal Differential Privacy Composition for Exponential Mechanisms and the Cost of Adaptivity
- Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models
- Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardware
- Private Prediction Sets
- Privacy-preserving Crowd-guided AI Decision-making in Ethical Dilemmas
- Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning
- On the Convergence and Calibration of Deep Learning with Differential Privacy
- Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information
- Privacy-preserving Learning via Deep Net Pruning
- FaceLeaks: Inference Attacks against Transfer Learning Models via Black-box Queries
- Locally Differentially Private Data Collection and Analysis
- PUMA: Secure Inference of LLaMA-7B in Five Minutes
- Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning
- Secure Deep Graph Generation with Link Differential Privacy
- Evading Curse of Dimensionality in Unconstrained Private GLMs via Private Gradient Descent
- Differentially Private Imaging via Latent Space Manipulation
- Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control
- Concentrated Differentially Private and Utility Preserving Federated Learning
- Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds
- Fast Dimension Independent Private AdaGrad on Publicly Estimated Subspaces
- Privacy-Preserving Gradient Boosting Decision Trees
- PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy
- Capacity Bounded Differential Privacy
- Data Privacy Preservation on the Internet of Things
- HDPView: Differentially Private Materialized View for Exploring High Dimensional Relational Data
- Differentially Private Learning of Undirected Graphical Models using Collective Graphical Models
- Efficient Per-Example Gradient Computations in Convolutional Neural Networks
- Differentially Private ADMM for Convex Distributed Learning: Improved Accuracy via Multi-Step Approximation
- Towards Fair Federated Learning with Zero-Shot Data Augmentation
- Practical One-Shot Federated Learning for Cross-Silo Setting
- Privacy-preserving Decentralized Aggregation for Federated Learning
- Gradient Perturbation is Underrated for Differentially Private Convex Optimization
- SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems
- Uncovering Gradient Inversion Risks in Practical Language Model Training
- Differentially Private Release of Israel's National Registry of Live Births
- NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks
- Benchmarking Differential Privacy and Federated Learning for BERT Models
- Privacy-preserving Federated Bayesian Learning of a Generative Model for Imbalanced Classification of Clinical Data
- Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
- Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection
- Distributed Differentially Private Computation of Functions with Correlated Noise
- Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment
- Dynamic Differential-Privacy Preserving SGD
- SoK: Training Machine Learning Models over Multiple Sources with Privacy Preservation
- Privacy-preserving machine learning with tensor networks
- Deep Learning Towards Mobile Applications
- Differentially Private Deep Learning with Smooth Sensitivity
- ER-AE: Differentially Private Text Generation for Authorship Anonymization
- Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps
- ASCAPE: An open AI ecosystem to support the quality of life of cancer patients
- FLea: Addressing Data Scarcity and Label Skew in Federated Learning via Privacy-preserving Feature Augmentation
- Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learning
- Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
- Differentially Private GANs for Generating Synthetic Indoor Location Data
- FLea: Addressing Data Scarcity and Label Skew in Federated Learning via Privacy-preserving Feature Augmentation
- Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
- Revealing the True Cost of Locally Differentially Private Protocols: An Auditing Perspective
- A Survey on Fault-tolerance in Distributed Optimization and Machine Learning
- Secure Mobile Crowdsensing with Deep Learning
- FedST: Secure Federated Shapelet Transformation for Time Series Classification
- Differential privacy and robust statistics in high dimensions
- On the Importance of Difficulty Calibration in Membership Inference Attacks
- Complex-valued Federated Learning with Differential Privacy and MRI Applications
- Hyperparameter Tuning with Renyi Differential Privacy
- Fair Sequential Selection Using Supervised Learning Models
- Dataset Meta-Learning from Kernel Ridge-Regression
- DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks
- On the Privacy Risks of Algorithmic Fairness
- Distributed Additive Encryption and Quantization for Privacy Preserving Federated Deep Learning
- Deep Learning with Label Differential Privacy
- Mitigating Sybil Attacks on Differential Privacy based Federated Learning
- TextHide: Tackling Data Privacy in Language Understanding Tasks
- Latent Dirichlet Allocation Model Training with Differential Privacy
- Differentially Private (Gradient) Expectation Maximization Algorithm with Statistical Guarantees
- Voting-based Approaches For Differentially Private Federated Learning
- Efficient Privacy Preserving Edge Computing Framework for Image Classification
- Conservative Plane Releasing for Spatial Privacy Protection in Mixed Reality
- On the Effectiveness of Regularization Against Membership Inference Attacks
- Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks
- Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms
- Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
- Improving Robustness to Model Inversion Attacks via Mutual Information Regularization
- Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness
- Actor Critic with Differentially Private Critic
- Privacy-preserving Q-Learning with Functional Noise in Continuous State Spaces
- Application-driven Privacy-preserving Data Publishing with Correlated Attributes
- Differentially Private Continual Learning
- Model-Agnostic Private Learning via Stability
- dpUGC: Learn Differentially Private Representation for User Generated Contents
- The Value of Collaboration in Convex Machine Learning with Differential Privacy
- Fairness-aware Differentially Private Collaborative Filtering
- Renyi Differential Privacy of the Subsampled Shuffle Model in Distributed Learning
- Private Stochastic Convex Optimization: Optimal Rates in Geometry
- Privacy Preserving Stochastic Channel-Based Federated Learning with Neural Network Pruning
- Generative Zero-shot Network Quantization
- Shredder: Learning Noise Distributions to Protect Inference Privacy
- Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks
- Differentially Private Deep Learning with Direct Feedback Alignment
- Federated Learning in Adversarial Settings
- Differentially Private Bayesian Inference for Generalized Linear Models
- A Privacy-Preserving Distributed Control of Optimal Power Flow
- Communication-Efficient Federated Learning with Compensated Overlap-FedAvg
- Tight and Robust Private Mean Estimation with Few Users
- Dr.Aid: Supporting Data-governance Rule Compliance for Decentralized Collaboration in an Automated Way
- DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
- PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
- Quantum delegated and federated learning via quantum homomorphic encryption
- Duet: An Expressive Higher-order Language and Linear Type System for Statically Enforcing Differential Privacy
- Improved Differentially Private Decentralized Source Separation for fMRI Data
- Low-Latency Federated Learning over Wireless Channels with Differential Privacy
- Differentially Private Synthetic Data Generation Using Context-Aware GANs
- Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach
- A Blockchain-Based Approach for Saving and Tracking Differential-Privacy Cost
- Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation
- Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification
- Methods for generating and evaluating synthetic longitudinal patient data: a systematic review
- Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning
- Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
- High Dimensional Model Explanations: an Axiomatic Approach
- On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach
- Stochastic Adaptive Line Search for Differentially Private Optimization
- Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
- Model Extraction and Defenses on Generative Adversarial Networks
- Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption
- Differentially Private Regression and Classification with Sparse Gaussian Processes
- Privacy-preserving Collaborative Learning with Automatic Transformation Search
- A Deep Learning Approach to Private Data Sharing of Medical Images Using Conditional GANs
- Data collaboration analysis for distributed datasets
- Generalization Techniques Empirically Outperform Differential Privacy against Membership Inference
- Synthetic Tabular Data: Methods, Attacks and Defenses
- Private Multi-Task Learning: Formulation and Applications to Federated Learning
- Private Meeting Summarization Without Performance Loss
- Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
- PrivColl: Practical Privacy-Preserving Collaborative Machine Learning
- Federated learning with differential privacy and an untrusted aggregator
- Label differential privacy via clustering
- StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting
- PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
- PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization
- Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling
- Differentially Private Convex Optimization with Feasibility Guarantees
- Machine Unlearning via Algorithmic Stability
- Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
- Using Decentralized Aggregation for Federated Learning with Differential Privacy
- Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning
- Lossless Compression of Efficient Private Local Randomizers
- An Analysis of the Deployment of Models Trained on Private Tabular Synthetic Data: Unexpected Surprises
- Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
- Super-convergence and Differential Privacy: Training faster with better privacy guarantees
- Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms
- The Differentially Private Lottery Ticket Mechanism
- Efficient Sparse Least Absolute Deviation Regression with Differential Privacy
- Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communication
- Robustness Threats of Differential Privacy
- P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model
- Near Instance-Optimality in Differential Privacy
- Policy-Based Federated Learning
- Bounding, Concentrating, and Truncating: Unifying Privacy Loss Composition for Data Analytics
- Differentially Private Distributed Computation via Public-Private Communication Networks
- Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling under Data Governance
- LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation
- Differential Private Stack Generalization with an Application to Diabetes Prediction
- Defending Medical Image Diagnostics against Privacy Attacks using Generative Methods
- A Fully Private Pipeline for Deep Learning on Electronic Health Records
- Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data
- A Lightweight Privacy-Preserving Scheme Using Label-based Pixel Block Mixing for Image Classification in Deep Learning
- Releasing Graph Neural Networks with Differential Privacy Guarantees
- A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations
- One-Shot Federated Learning with Neuromorphic Processors
- Robust and Private Learning of Halfspaces
- EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning
- Federated Learning for Open Banking
- Improved Matrix Gaussian Mechanism for Differential Privacy
- Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning
- Privacy Preserving Conversion Modeling in Data Clean Room
- Effective and Privacy preserving Tabular Data Synthesizing
- Perun: Secure Multi-Stakeholder Machine Learning Framework with GPU Support
- Robustness, Privacy, and Generalization of Adversarial Training
- DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
- Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent
- DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning
- Review learning: Real world validation of privacy preserving continual learning across medical institutions
- Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT
- Privacy-Preserving Kickstarting Deep Reinforcement Learning with Privacy-Aware Learners
- On the Differential Private Data Market: Endogenous Evolution, Dynamic Pricing, and Incentive Compatibility
- Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)
- Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning
- Federated Unlearning
- Differentially Private Decentralized Optimization with Relay Communication
- GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning
- DPD-InfoGAN: Differentially Private Distributed InfoGAN
- Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
- P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification
- Trustworthy AI Inference Systems: An Industry Research View
- Model-based Differentially Private Data Synthesis and Statistical Inference in Multiply Synthetic Differentially Private Data
- Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
- Energy cost and machine learning accuracy impact of k-anonymisation and synthetic data techniques
- Distributed Optimization for Client-Server Architecture with Negative Gradient Weights
- Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT
- Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?
- Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data
- DP-REC: Private & Communication-Efficient Federated Learning
- Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
- On Large-Cohort Training for Federated Learning
- Towards practical differentially private causal graph discovery
- Optimizing Privacy-Preserving Outsourced Convolutional Neural Network Predictions
- Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation
- Differentially Private Data Generation with Missing Data
- Survey on AI Ethics: A Socio-technical Perspective
- Decaffe: DHT Tree-Based Online Federated Fake News Detection
- The Trade-Offs of Private Prediction
- Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
- Differentially Private Variational Dropout
- Privacy-Preserving Distributed Zeroth-Order Optimization
- SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
- Secure Data Sharing With Flow Model
- Learning to Succeed while Teaching to Fail: Privacy in Closed Machine Learning Systems
- Deep Learning Application in Security and Privacy -- Theory and Practice: A Position Paper
- Membership Inference Attacks Against Object Detection Models
- Privacy-Preserving Collaborative Deep Learning with Unreliable Participants
- PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy
- Local Differential Privacy in Decentralized Optimization
- Public Data-Assisted Mirror Descent for Private Model Training
- The Connection between Out-of-Distribution Generalization and Privacy of ML Models
- Node-Level Differentially Private Graph Neural Networks
- On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models
- Assisted Learning for Organizations with Limited Imbalanced Data
- Accelerating Federated Learning in Heterogeneous Data and Computational Environments
- When Differential Privacy Meets Interpretability: A Case Study
- SMAP: A Joint Dimensionality Reduction Scheme for Secure Multi-Party Visualization
- Towards Distributed Privacy-Preserving Prediction
- Noise Variance Optimization in Differential Privacy: A Game-Theoretic Approach Through Per-Instance Differential Privacy
- Differentially Private Federated Learning via Inexact ADMM
- DPack: Efficiency-Oriented Privacy Budget Scheduling
- Private Optimization Without Constraint Violations
- Adaptive Differentially Private Empirical Risk Minimization
- Constrained Differentially Private Federated Learning for Low-bandwidth Devices
- Federated Survival Analysis with Discrete-Time Cox Models
- On Connecting Stochastic Gradient MCMC and Differential Privacy
- Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
- Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation
- Memorization of Named Entities in Fine-tuned BERT Models
- Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning
- Can Differential Privacy Practically Protect Collaborative Deep Learning Inference for the Internet of Things?
- Federated machine learning with Anonymous Random Hybridization (FeARH) on medical records
- An Empirical Study on the Intrinsic Privacy of SGD
- Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
- Disentangling private classes through regularization
- A Communication-efficient Local Differentially Private Algorithm in Federated Optimization
- Optimizing Fitness-For-Use of Differentially Private Linear Queries
- Decentralized Differentially Private Without-Replacement Stochastic Gradient Descent
- Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
- RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
- Correlated Data in Differential Privacy: Definition and Analysis
- Disclosure Risk from Homogeneity Attack in Differentially Private Frequency Distribution
- Obfuscation of Images via Differential Privacy: From Facial Images to General Images
- An Efficient DP-SGD Mechanism for Large Scale NLP Models
- DPCOVID: Privacy-Preserving Federated Covid-19 Detection
- From Private to Public: Benchmarking GANs in the Context of Private Time Series Classification
- Masked LARk: Masked Learning, Aggregation and Reporting worKflow
- Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
- Domain Impression: A Source Data Free Domain Adaptation Method
- Boosting Model Performance through Differentially Private Model Aggregation
- Unsupervised Geometric Disentanglement for Surfaces via CFAN-VAE
- When Homomorphic Cryptosystem Meets Differential Privacy: Training Machine Learning Classifier with Privacy Protection
- Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
- Reaching Data Confidentiality and Model Accountability on the CalTrain
- Adapting to Function Difficulty and Growth Conditions in Private Optimization
- Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
- Improving Differentially Private Models with Active Learning
- Privacy Preserving Machine Learning: Threats and Solutions
- A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes
- Trading Data For Learning: Incentive Mechanism For On-Device Federated Learning
- Fuzzi: A Three-Level Logic for Differential Privacy
- Privacy-Preserving Machine Learning in Untrusted Clouds Made Simple
- Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data
- Utility-aware Privacy-preserving Data Releasing
- GDRQ: Group-based Distribution Reshaping for Quantization
- Synthetic Trajectory Generation Through Convolutional Neural Networks
- Detection of Lying Electrical Vehicles in Charging Coordination Application Using Deep Learning
- The Influence of Dropout on Membership Inference in Differentially Private Models
- Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms
- Exploring the Unfairness of DP-SGD Across Settings
- Information-constrained optimization: can adaptive processing of gradients help?
- Differentially Private Adapters for Parameter Efficient Acoustic Modeling
- A Differentially Private Multi-Output Deep Generative Networks Approach For Activity Diary Synthesis
- Oneshot Differentially Private Top-k Selection
- Communication Efficient Federated Learning with Adaptive Quantization
- Inferring Communities of Interest in Collaborative Learning-based Recommender Systems
- TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing
- Generative Models for Security: Attacks, Defenses, and Opportunities
- Network Generation with Differential Privacy
- Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methods
- D3p -- A Python Package for Differentially-Private Probabilistic Programming
- Median regression with differential privacy
- An automatic differentiation system for the age of differential privacy
- AHEAD: Adaptive Hierarchical Decomposition for Range Query under Local Differential Privacy
- Interpretable collaborative data analysis on distributed data
- MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning
- SSGD: A safe and efficient method of gradient descent
- Towards Differentially Private Text Representations
- Security and Privacy Preserving Deep Learning
- Secure Machine Learning over Relational Data
- High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent
- Privately Learning Subspaces
- Syft 0.5: A Platform for Universally Deployable Structured Transparency
- Modelos dinâmicos aplicados à aprendizagem de valores em inteligência artificial
- Data-Free Evaluation of User Contributions in Federated Learning
- GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks
- On the Intrinsic Differential Privacy of Bagging
- H-FL: A Hierarchical Communication-Efficient and Privacy-Protected Architecture for Federated Learning
- GRAFFL: Gradient-free Federated Learning of a Bayesian Generative Model
- PPVF: An Efficient Privacy-Preserving Online Video Fetching Framework with Correlated Differential Privacy
- Utility Fairness for the Differentially Private Federated Learning
- An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks
- Maximal Information Leakage based Privacy Preserving Data Disclosure Mechanisms
- Privacy-Preserving Machine Learning Training in Aggregation Scenarios
- Data Poisoning and Leakage Analysis in Federated Learning
- Private Deep Learning with Teacher Ensembles
- Private Hierarchical Clustering and Efficient Approximation
- Federated Learning With Individualized Privacy Through Client Sampling
- Free Gap Information from the Differentially Private Sparse Vector and Noisy Max Mechanisms
- Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
- Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifiers
- Who started this rumor? Quantifying the natural differential privacy guarantees of gossip protocols
- Differentially Private Federated Variational Inference
- LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning
- An Adaptive and Fast Convergent Approach to Differentially Private Deep Learning
- Do Not Return Similarity: Face Recovery with Distance
- DP-CGAN: Differentially Private Synthetic Data and Label Generation
- Do I Get the Privacy I Need? Benchmarking Utility in Differential Privacy Libraries
- Task-aware Privacy Preservation for Multi-dimensional Data
- FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
- Sharper Utility Bounds for Differentially Private Models
- Differentially Private M-band Wavelet-Based Mechanisms in Machine Learning Environments
- Distributed Deep Learning for Medical Image Denoising with Data Obfuscation
- Heavy-tailed Streaming Statistical Estimation
- Gain without Pain: Offsetting DP-injected Nosies Stealthily in Cross-device Federated Learning
- Improving Utility of Differentially Private Mechanisms through Cryptography-based Technologies: a Survey
- Privacy-preserving Channel Estimation in Cell-free Hybrid Massive MIMO Systems
- From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning
- Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
- An Analysis Of Protected Health Information Leakage In Deep-Learning Based De-Identification Algorithms
- Privacy-preserving Data Sharing on Vertically Partitioned Data
- Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data
- Composable Generative Models
- Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
- Quantifying Membership Privacy via Information Leakage
- A Human-Centered Privacy Approach (HCP) to AI
- Local SGD for Near-Quadratic Problems: Improving Convergence under Unconstrained Noise Conditions
- Hierarchical Online Convex Optimization
- Gaussian Processes with Differential Privacy
- Improving Differentially Private SGD via Randomly Sparsified Gradients
- Accelerated Stochastic ExtraGradient: Mixing Hessian and Gradient Similarity to Reduce Communication in Distributed and Federated Learning
- Semi-Federated Learning
- On Privacy and Confidentiality of Communications in Organizational Graphs
- Amplifying Rényi Differential Privacy via Shuffling
- Protecting Big Data Privacy Using Randomized Tensor Network Decomposition and Dispersed Tensor Computation
- BadVFL: Backdoor Attacks in Vertical Federated Learning
- Taming Distrust in the Decentralized Internet with PIXIU
- Community Preserved Social Graph Publishing with Node Differential Privacy
- Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery
- Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques
- Causally Constrained Data Synthesis for Private Data Release
- Secure Metric Learning via Differential Pairwise Privacy
- Sometimes You Want to Go Where Everybody Knows your Name
- DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing
- Combining Differential Privacy and Byzantine Resilience in Distributed SGD
- BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation
- Privacy accounting conomics: Improving differential privacy composition via a posteriori bounds
- Tensorization of neural networks for improved privacy and interpretability
- Renyi Differentially Private ADMM for Non-Smooth Regularized Optimization
- Private Knowledge Transfer via Model Distillation with Generative Adversarial Networks
- DuetSGX: Differential Privacy with Secure Hardware
- Littlestone Classes are Privately Online Learnable
- Accuracy Gains from Privacy Amplification Through Sampling for Differential Privacy
- Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling
- A Survey on Threat Situation Awareness Systems: Framework, Techniques, and Insights
- ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning
- FedOptima: Optimizing Resource Utilization in Federated Learning
- Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization
- Differentially Private ADMM Algorithms for Machine Learning
- Towards Explainable Multi-Party Learning: A Contrastive Knowledge Sharing Framework
- Splintering with distributions: A stochastic decoy scheme for private computation
- Differentially Private Multivariate Statistics with an Application to Contingency Table Analysis
- A Novel Approach to Differential Privacy with Alpha Divergence
- User-centric Composable Services: A New Generation of Personal Data Analytics
- Learning Realistic Patterns from Unrealistic Stimuli: Generalization and Data Anonymization
- Partial sensitivity analysis in differential privacy
- Privacy-Preserving Public Release of Datasets for Support Vector Machine Classification
- Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty
- Robust and Differentially Private Principal Component Analysis
- The Relative Gaussian Mechanism and its Application to Private Gradient Descent
- DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?
- Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
- On the Differentially Private Nature of Perturbed Gradient Descent
- Differentially Private Densest Subgraph Detection
- Multi-Party Dual Learning
- One-Bit Matrix Completion with Differential Privacy
- Adversarial Data Encryption
- Balance is key: Private median splits yield high-utility random trees
- A Graph Symmetrisation Bound on Channel Information Leakage under Blowfish Privacy
- Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challenges
- PUTWorkbench: Analysing Privacy in AI-intensive Systems
- Prior-Independent Auctions for the Demand Side of Federated Learning
- FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data
- A Privacy-Preserving and Trustable Multi-agent Learning Framework
- TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data
- Byzantine-Resilient Federated Machine Learning via Over-the-Air Computation
- Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud
- Privacy-Preserving Portrait Matting
- Privacy-Aware Document Visual Question Answering
- Bilevel Optimization for Differentially Private Optimization in Energy Systems
- IRG: Modular Synthetic Relational Database Generation with Complex Relational Schemas
- Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent
- Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems
- Continuous Latent Process Flows
- A closed form scale bound for the -differentially private Gaussian Mechanism valid for all privacy regimes
- Reducing Risk of Model Inversion Using Privacy-Guided Training
- Flexible Accuracy for Differential Privacy
- Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
- Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education
- On Privacy Protection of Latent Dirichlet Allocation Model Training
- MYSTIKO : : Cloud-Mediated, Private, Federated Gradient Descent
- Rejoinder: Gaussian Differential Privacy
- Against Membership Inference Attack: Pruning is All You Need
- CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale
- A Robust Framework for Secure Cardiovascular Risk Prediction: An Architectural Case Study of Differentially Private Federated Learning
- SoK: Practical Aspects of Releasing Differentially Private Graphs
- Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design
- CatFedAvg: Optimising Communication-efficiency and Classification Accuracy in Federated Learning
- Corella: A Private Multi Server Learning Approach based on Correlated Queries
- Privately Answering Queries on Skewed Data via Per Record Differential Privacy
- Not Just Cloud Privacy: Protecting Client Privacy in Teacher-Student Learning
- Towards Sharper Utility Bounds for Differentially Private Pairwise Learning
- Gradient-Leakage Resilient Federated Learning
- Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning
- Integrating Homomorphic Encryption and Synthetic Data in FL for Privacy and Learning Quality
- Towards Efficient and Secure Delivery of Data for Deep Learning with Privacy-Preserving
- Efficient Private Machine Learning by Differentiable Random Transformations
- Towards Efficient and Secure Delivery of Data for Training and Inference with Privacy-Preserving
- Regularized Loss Minimizers with Local Data Perturbation: Consistency and Data Irrecoverability
- Auditing Differential Privacy Guarantees Using Density Estimation
- Statistical Guarantees for Fairness Aware Plug-In Algorithms
- Topology-aware Differential Privacy for Decentralized Image Classification
- Efficient Hyperparameter Optimization for Differentially Private Deep Learning
- NegDL: Privacy-Preserving Deep Learning Based on Negative Database
- Privacy-Preserving Bandits
- What Storage Access Privacy is Achievable with Small Overhead?
- Selective Differential Privacy for Language Modeling
- Privacy enabled Financial Text Classification using Differential Privacy and Federated Learning
- Confidential Machine Learning on Untrusted Platforms: A Survey
- Privacy Amplification via Iteration for Shuffled and Online PNSGD
- Differentially Private Generation of Small Images
- Differentially Private Link Prediction With Protected Connections