Deep Learning with Differential Privacy

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 (7)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Deep Learning with Differential Privacy
• Renyi Differential Privacy
• Grammar as a Foreign Language
• Fractional Max-Pooling
• Move Evaluation in Go Using Deep Convolutional Neural Networks
• Privacy Odometers and Filters: Pay-as-you-Go Composition

Cited by in corpus (924)

• 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
• 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
• DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments
• DP-ADMM: ADMM-based Distributed Learning with Differential Privacy
• Practical Secure Aggregation for Federated Learning on User-Held Data
• 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
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Differentially Private Synthetic Medical Data Generation using Convolutional GANs
• 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
• Privacy Amplification by Iteration
• Quantum federated learning through blind quantum computing
• GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learning
• Privacy-Preserving Deep Learning via Weight Transmission
• Abnormal Client Behavior Detection in Federated Learning
• IBM Federated Learning: an Enterprise Framework White Paper V0.1
• 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
• A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysis
• From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security
• Correlated Differential Privacy: Feature Selection in Machine Learning
• 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
• When Machine Learning Meets Privacy: A Survey and Outlook
• Label-Only Membership Inference Attacks
• Preserving Privacy and Security in Federated Learning
• Quantifying Privacy Leakage in Graph Embedding
• Over-the-Air Computation for 6G: Foundations, Technologies, and Applications
• Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer
• Domain Generalization for Medical Image Analysis: A Review
• Practical Blind Membership Inference Attack via Differential Comparisons
• Analyzing Information Leakage of Updates to Natural Language Models
• Unsolved Problems in ML Safety
• Federated Learning with Differential Privacy: Algorithms and Performance Analysis
• VAFL: a Method of Vertical Asynchronous Federated Learning
• A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning
• Rényi Differential Privacy of the Sampled Gaussian Mechanism
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• PPGAN: Privacy-preserving Generative Adversarial Network
• Differentially Private Learning with Adaptive Clipping
• Systematic Evaluation of Privacy Risks of Machine Learning Models
• Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses
• Evaluating Differentially Private Machine Learning in Practice
• 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
• Efficient Deep Learning on Multi-Source Private Data
• Artificial Intelligence of Things: A Survey
• Large Language Models Can Be Strong Differentially Private Learners
• A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources
• Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
• A Hybrid Approach to Privacy-Preserving Federated Learning
• On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
• Free-riders in Federated Learning: Attacks and Defenses
• 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
• An Efficient and Scalable Privacy Preserving Algorithm for Big Data and Data Streams
• A Survey of Privacy Vulnerabilities of Mobile Device Sensors
• Federated Learning for Healthcare Informatics
• A Study of Face Obfuscation in ImageNet
• Differentially Private Learning Needs Better Features (or Much More Data)
• Scalable and Differentially Private Distributed Aggregation in the Shuffled Model
• Local Differential Privacy and Its Applications: A Comprehensive Survey
• Label Leakage and Protection in Two-party Split Learning
• Differential Privacy for Eye-Tracking Data
• Privacy-preserving Federated Brain Tumour Segmentation
• Membership Inference Attacks and Defenses in Classification Models
• 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
• 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
• Defending Model Inversion and Membership Inference Attacks via Prediction Purification
• A Safety Framework for Critical Systems Utilising Deep Neural Networks
• Throughput-Optimal Topology Design for Cross-Silo Federated Learning
• A blockchain-orchestrated Federated Learning architecture for healthcare consortia
• ScaleSFL: A Sharding Solution for Blockchain-Based Federated Learning
• DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass
• FedDef: Defense Against Gradient Leakage in Federated Learning-based Network Intrusion Detection Systems
• Communication-Computation Efficient Secure Aggregation for Federated Learning
• Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
• RAB: Provable Robustness Against Backdoor Attacks
• Differentially Private Fine-tuning of Language Models
• DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
• Oort: Efficient Federated Learning via Guided Participant Selection
• The Cost of Privacy: Rates of Convergence for Parameter Estimation with Differential Privacy
• The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
• Generative adversarial networks in time series: A survey and taxonomy
• Unlearnable Examples: Making Personal Data Unexploitable
• AutoGAN-based Dimension Reduction for Privacy Preservation
• 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
• Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
• Privacy and Trust Redefined in Federated Machine Learning
• Privacy-preserving parametric inference: a case for robust statistics
• Natural Language Understanding with Privacy-Preserving BERT
• Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
• Generative Models for Effective ML on Private, Decentralized Datasets
• Dopamine: Differentially Private Federated Learning on Medical Data
• 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
• SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregation
• FederBoost: Private Federated Learning for GBDT
• 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
• Privacy Adversarial Network: Representation Learning for Mobile Data Privacy
• Federated Learning with Buffered Asynchronous Aggregation
• Computing Local Sensitivities of Counting Queries with Joins
• The Skellam Mechanism for Differentially Private Federated Learning
• secureTF: A Secure TensorFlow Framework
• Exploring Design and Governance Challenges in the Development of Privacy-Preserving Computation
• Privacy Management and Optimal Pricing in People-Centric Sensing
• Towards Probabilistic Verification of Machine Unlearning
• Privacy Accounting and Quality Control in the Sage Differentially Private ML Platform
• Generative Models for Synthetic Urban Mobility Data: A Systematic Literature Review
• 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
• Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
• A Federated Deep Learning Framework for Privacy Preservation and Communication Efficiency
• Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation
• Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
• The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
• Fed-Focal Loss for imbalanced data classification in Federated Learning
• Federated Boosted Decision Trees with Differential Privacy
• Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates
• Radioactive data: tracing through training
• Health Data in an Open World
• 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
• Adversarial Examples Make Strong Poisons
• Stochastic, Distributed and Federated Optimization for Machine Learning
• Gradient Centralization: A New Optimization Technique for Deep Neural Networks
• Learning Privately over Distributed Features: An ADMM Sharing Approach
• Coded Machine Unlearning
• Machine Learning Models that Remember Too Much
• Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey
• Differentially Private Data Generative Models
• How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning
• A Customized Text Sanitization Mechanism with Differential Privacy
• GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
• Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)
• Improving the utility of locally differentially private protocols for longitudinal and multidimensional frequency estimates
• Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning
• Pointwise Maximal Leakage
• GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions
• Synthesis of Realistic ECG using Generative Adversarial Networks
• FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction
• Leakage of Dataset Properties in Multi-Party Machine Learning
• Secure Federated Submodel Learning
• LinkedIn's Audience Engagements API: A Privacy Preserving Data Analytics System at Scale
• Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
• Learning Adversary-Resistant Deep Neural Networks
• Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
• HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
• Privado: Practical and Secure DNN Inference with Enclaves
• Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning
• Asynchronous Federated Learning with Differential Privacy for Edge Intelligence
• Successive Point-of-Interest Recommendation with Local Differential Privacy
• Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results
• Practical Vertical Federated Learning with Unsupervised Representation Learning
• Forecasting: theory and practice
• Differentially Private Federated Clustering over Non-IID Data
• Practical Defences Against Model Inversion Attacks for Split Neural Networks
• Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries
• GAMIN: An Adversarial Approach to Black-Box Model Inversion
• Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems
• Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
• Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
• Distributed Training of Graph Convolutional Networks
• Privacy-preserving machine learning for healthcare: open challenges and future perspectives
• Personalized Federated Learning with First Order Model Optimization
• Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
• Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
• Differentially-Private "Draw and Discard" Machine Learning
• Random Sampling Plus Fake Data: Multidimensional Frequency Estimates With Local Differential Privacy
• Differentially Private Synthetic Data: Applied Evaluations and Enhancements
• Social-Aware Clustered Federated Learning with Customized Privacy Preservation
• Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment
• Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-Coded Credentials
• DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy
• Hypothesis Testing Interpretations and Renyi Differential Privacy
• The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
• LDP-Fed: Federated Learning with Local Differential Privacy
• DP-BART for Privatized Text Rewriting under Local Differential Privacy
• A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
• Guidelines for Implementing and Auditing Differentially Private Systems
• Differentially Private Federated Learning on Heterogeneous Data
• Approximate Span Liftings
• Effectiveness of Distillation Attack and Countermeasure on Neural Network Watermarking
• Federated Reconstruction: Partially Local Federated Learning
• Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices
• Privacy Meets Explainability: A Comprehensive Impact Benchmark
• Locally Differentially Private Heavy Hitter Identification
• Differential Privacy in Natural Language Processing: The Story So Far
• Enhancing the Privacy of Federated Learning with Sketching
• Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
• Reversible Privacy Preservation using Multi-level Encryption and Compressive Sensing
• Privacy-Preserving Ensemble Infused Enhanced Deep Neural Network Framework for Edge Cloud Convergence
• DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation
• Opacus: User-Friendly Differential Privacy Library in PyTorch
• Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
• 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
• Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising
• Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications
• A Survey on Privacy-Preserving Caching at Network Edge: Classification, Solutions, and Challenges
• Personality testing of Large Language Models: Limited temporal stability, but highlighted prosociality
• Practical and Private (Deep) Learning without Sampling or Shuffling
• Poisoning the Unlabeled Dataset of Semi-Supervised Learning
• Differentially private cross-silo federated learning
• Recent advances in deep learning theory
• Hybrid Differentially Private Federated Learning on Vertically Partitioned Data
• Privacy-preserving quantum federated learning via gradient hiding
• Training Data Leakage Analysis in Language Models
• Greedy Shapley Client Selection for Communication-Efficient Federated Learning
• Differentially Private Empirical Risk Minimization Revisited: Faster and More General
• Individual Privacy Accounting via a Renyi Filter
• Edge-cloud Collaborative Learning with Federated and Centralized Features
• Membership Inference Attack Susceptibility of Clinical Language Models
• Practical Differentially Private and Byzantine-resilient Federated Learning
• Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification
• Differentially Private Vertical Federated Clustering
• Cloud2Edge Elastic AI Framework for Prototyping and Deployment of AI Inference Engines in Autonomous Vehicles
• Certified Data Removal from Machine Learning Models
• Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization
• Handcrafted Backdoors in Deep Neural Networks
• Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms
• Private Model Compression via Knowledge Distillation
• Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications
• DP-LSTM: Differential Privacy-inspired LSTM for Stock Prediction Using Financial News
• InstaHide: Instance-hiding Schemes for Private Distributed Learning
• Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity
• Explainable Differential Privacy-Hyperdimensional Computing for Balancing Privacy and Transparency in Additive Manufacturing Monitoring
• Reviewing and Improving the Gaussian Mechanism for Differential Privacy
• Predominant Aspects on Security for Quantum Machine Learning: Literature Review
• Is Your Model Sensitive? SPeDaC: A New Benchmark for Detecting and Classifying Sensitive Personal Data
• DEEProtect: Enabling Inference-based Access Control on Mobile Sensing Applications
• Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning
• Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization
• The Impact of Speech Anonymization on Pathology and Its Limits
• Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses
• Federated Learning of N-gram Language Models
• Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
• SPEED: Secure, PrivatE, and Efficient Deep learning
• Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning
• Differentially Private Federated Learning for Resource-Constrained Internet of Things
• DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
• DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM
• A Differentially Private Framework for Deep Learning with Convexified Loss Functions
• Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase
• Knowledge Cross-Distillation for Membership Privacy
• Pain-Free Random Differential Privacy with Sensitivity Sampling
• On Safeguarding Privacy and Security in the Framework of Federated Learning
• Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise
• Robust Distributed Optimization With Randomly Corrupted Gradients
• Differential Privacy for Government Agencies -- Are We There Yet?
• Self-supervised Cross-silo Federated Neural Architecture Search
• Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection
• A Federated Multi-View Deep Learning Framework for Privacy-Preserving Recommendations
• PPaaS: Privacy Preservation as a Service
• Training Production Language Models without Memorizing User Data
• Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection
• Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings
• Anonymizing Machine Learning Models
• Differentially Private Federated Learning for Cancer Prediction
• Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy
• Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
• That which we call private
• A Theoretical Perspective on Differentially Private Federated Multi-task Learning
• Privacy-Preserving Individual-Level COVID-19 Infection Prediction via Federated Graph Learning
• Differentially Private Generative Adversarial Networks with Model Inversion
• An Overview of Privacy in Machine Learning
• COVID-19 Imaging Data Privacy by Federated Learning Design: A Theoretical Framework
• CAFE: Catastrophic Data Leakage in Vertical Federated Learning
• Assessing differentially private deep learning with Membership Inference
• Fast-adapting and Privacy-preserving Federated Recommender System
• Mechanism Design for Multi-Party Machine Learning
• Membership Leakage in Label-Only Exposures
• Investigating the Significance of the Bellwether Effect to Improve Software Effort Prediction: Further Empirical Study
• Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification
• Differentially Private Accelerated Optimization Algorithms
• Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry
• Membership Inference on Word Embedding and Beyond
• TransMIA: Membership Inference Attacks Using Transfer Shadow Training
• Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
• DarKnight: A Data Privacy Scheme for Training and Inference of Deep Neural Networks
• Detecting Violations of Differential Privacy for Quantum Algorithms
• How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning
• SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability
• Large Scale Private Learning via Low-rank Reparametrization
• Dordis: Efficient Federated Learning with Dropout-Resilient Differential Privacy
• Characterizing and Optimizing End-to-End Systems for Private Inference
• Propose, Test, Release: Differentially private estimation with high probability
• Bounding Information Leakage in Machine Learning
• CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU
• Optimal Accounting of Differential Privacy via Characteristic Function
• 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
• Understanding Compressive Adversarial Privacy
• A Privacy-Preserving Federated Framework with Hybrid Quantum-Enhanced Learning for Financial Fraud Detection
• Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
• Group privacy for personalized federated learning
• Private Learning on Networks: Part II
• Optimal query complexity for private sequential learning against eavesdropping
• RDP-GAN: A Rényi-Differential Privacy based Generative Adversarial Network
• Aggregation and Transformation of Vector-Valued Messages in the Shuffle Model of Differential Privacy
• User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization
• Layer-wise Characterization of Latent Information Leakage in Federated Learning
• Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning
• FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training
• Information Leakage in Embedding Models
• The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Bounds
• On the Impact of Device and Behavioral Heterogeneity in Federated Learning
• Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent Agents
• Privacy for All: Demystify Vulnerability Disparity of Differential Privacy against Membership Inference Attack
• A Comprehensive Analysis of Information Leakage in Deep Transfer Learning
• LOGAN: Membership Inference Attacks Against Generative Models
• Robust and Differentially Private Mean Estimation
• Helen: Maliciously Secure Coopetitive Learning for Linear Models
• Fed-BioMed: Open, Transparent and Trusted Federated Learning for Real-world Healthcare Applications
• FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions
• Private Post-GAN Boosting
• Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs
• Computing Tight Differential Privacy Guarantees Using FFT
• Efficient Cybersecurity Assessment Using SVM and Fuzzy Evidential Reasoning for Resilient Infrastructure
• Differentially Private False Discovery Rate Control
• MOBIUS: Model-Oblivious Binarized Neural Networks
• Differentially Private Publication of Location Entropy
• SoK: Machine Learning Governance
• Is Private Learning Possible with Instance Encoding?
• Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond
• privGAN: Protecting GANs from membership inference attacks at low cost
• PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning
• Representation Transfer for Differentially Private Drug Sensitivity Prediction
• MixNN: Protection of Federated Learning Against Inference Attacks by Mixing Neural Network Layers
• Efficient Privacy-Preserving Stochastic Nonconvex Optimization
• Towards Security Threats of Deep Learning Systems: A Survey
• Network Shuffling: Privacy Amplification via Random Walks
• Private Learning on Networks
• Instance-optimal Mean Estimation Under Differential Privacy
• Privacy-Preserving Distributed Expectation Maximization for Gaussian Mixture Model using Subspace Perturbation
• Blockchain-Based Federated Learning in Mobile Edge Networks with Application in Internet of Vehicles
• Defending against Reconstruction Attack in Vertical Federated Learning
• Image Obfuscation for Privacy-Preserving Machine Learning
• Learning Rate Adaptation for Federated and Differentially Private Learning
• SoK: Dataset Copyright Auditing in Machine Learning Systems
• Improved Analysis of Clipping Algorithms for Non-convex Optimization
• Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack
• Quantum-machine-assisted Drug Discovery
• Input Perturbation: A New Paradigm between Central and Local Differential Privacy
• From Federated Learning to Federated Neural Architecture Search: A Survey
• Quantifying Membership Inference Vulnerability via Generalization Gap and Other Model Metrics
• Key Protected Classification for Collaborative Learning
• Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation
• On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
• Pufferfish Privacy: An Information-Theoretic Study
• Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?
• NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets
• CryptoNN: Training Neural Networks over Encrypted Data
• Bayesian Differential Privacy for Machine Learning
• DistFL: Distribution-aware Federated Learning for Mobile Scenarios
• Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget
• Differentially Private Federated Learning with Laplacian Smoothing
• Privacy-Preserving Models for Legal Natural Language Processing
• DTGAN: Differential Private Training for Tabular GANs
• Secure Linear Aggregation Using Decentralized Threshold Additive Homomorphic Encryption For Federated Learning
• The More, the Better? A Study on Collaborative Machine Learning for DGA Detection
• Weighted Distributed Differential Privacy ERM: Convex and Non-convex
• Benchmarking Secure Sampling Protocols for Differential Privacy
• Stochastic Channel-Based Federated Learning for Medical Data Privacy Preserving
• Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch
• Toward an Automated Auction Framework for Wireless Federated Learning Services Market
• CaPC Learning: Confidential and Private Collaborative Learning
• Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data
• Kamino: Constraint-Aware Differentially Private Data Synthesis
• Federated $f$-Differential Privacy
• Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraints
• Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings
• Anonymizing Data for Privacy-Preserving Federated Learning
• Element Level Differential Privacy: The Right Granularity of Privacy
• Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy
• Arbitrary Decisions are a Hidden Cost of Differentially Private Training
• Wide Network Learning with Differential Privacy
• A General Framework for Data-Use Auditing of ML Models
• KiNETGAN: Enabling Distributed Network Intrusion Detection through Knowledge-Infused Synthetic Data Generation
• 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
• Locally Differentially Private Data Collection and Analysis
• FaceLeaks: Inference Attacks against Transfer Learning Models via Black-box Queries
• Privacy-preserving Crowd-guided AI Decision-making in Ethical Dilemmas
• Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control
• Secure Deep Graph Generation with Link Differential Privacy
• Concentrated Differentially Private and Utility Preserving Federated Learning
• PUMA: Secure Inference of LLaMA-7B in Five Minutes
• Fast and Memory Efficient Differentially Private-SGD via JL Projections
• Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information
• PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy
• Privacy-Preserving Gradient Boosting Decision Trees
• Differentially Private Imaging via Latent Space Manipulation
• Privacy-preserving Non-negative Matrix Factorization with Outliers
• Advances in Differential Privacy and Differentially Private Machine Learning
• Fast Dimension Independent Private AdaGrad on Publicly Estimated Subspaces
• Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning
• On the Convergence and Calibration of Deep Learning with Differential Privacy
• Privacy-preserving Learning via Deep Net Pruning
• Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardware
• Generation of Differentially Private Heterogeneous Electronic Health Records
• A(DP)${}^2$SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy
• Federated Learning in Mobile Edge Computing: An Edge-Learning Perspective for Beyond 5G
• Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds
• UniHENN: Designing Faster and More Versatile Homomorphic Encryption-based CNNs without im2col
• Private Prediction Sets
• Practical Privacy Filters and Odometers with Rényi Differential Privacy and Applications to Differentially Private Deep Learning
• Evading Curse of Dimensionality in Unconstrained Private GLMs via Private Gradient Descent
• Private Collaborative Edge Inference via Over-the-Air Computation
• SoK: Training Machine Learning Models over Multiple Sources with Privacy Preservation
• Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
• Deep Learning Towards Mobile Applications
• Gradient Perturbation is Underrated for Differentially Private Convex Optimization
• Differentially Private ADMM for Convex Distributed Learning: Improved Accuracy via Multi-Step Approximation
• Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection
• Privacy-preserving machine learning with tensor networks
• Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment
• Dynamic Differential-Privacy Preserving SGD
• Privacy-preserving Decentralized Aggregation for Federated Learning
• Benchmarking Differential Privacy and Federated Learning for BERT Models
• Differentially Private Deep Learning with Smooth Sensitivity
• Towards Fair Federated Learning with Zero-Shot Data Augmentation
• NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks
• Differentially Private Learning of Undirected Graphical Models using Collective Graphical Models
• Efficient Per-Example Gradient Computations in Convolutional Neural Networks
• Differentially Private Release of Israel's National Registry of Live Births
• Uncovering Gradient Inversion Risks in Practical Language Model Training
• Capacity Bounded Differential Privacy
• Data Privacy Preservation on the Internet of Things
• Privacy-preserving Federated Bayesian Learning of a Generative Model for Imbalanced Classification of Clinical Data
• SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems
• ER-AE: Differentially Private Text Generation for Authorship Anonymization
• Distributed Differentially Private Computation of Functions with Correlated Noise
• HDPView: Differentially Private Materialized View for Exploring High Dimensional Relational Data
• Practical One-Shot Federated Learning for Cross-Silo Setting
• Latent Dirichlet Allocation Model Training with Differential Privacy
• Distributed Additive Encryption and Quantization for Privacy Preserving Federated Deep Learning
• On the Privacy Risks of Algorithmic Fairness
• Dataset Meta-Learning from Kernel Ridge-Regression
• Fair Sequential Selection Using Supervised Learning Models
• Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps
• A Survey on Fault-tolerance in Distributed Optimization and Machine Learning
• Model-Agnostic Private Learning via Stability
• Conservative Plane Releasing for Spatial Privacy Protection in Mixed Reality
• Fairness-aware Differentially Private Collaborative Filtering
• 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
• The Value of Collaboration in Convex Machine Learning with Differential Privacy
• On the Effectiveness of Regularization Against Membership Inference Attacks
• 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
• Application-driven Privacy-preserving Data Publishing with Correlated Attributes
• Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks
• FedST: Secure Federated Shapelet Transformation for Time Series Classification
• Secure Mobile Crowdsensing with Deep Learning
• Privacy-preserving Q-Learning with Functional Noise in Continuous State Spaces
• 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
• Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms
• Hyperparameter Tuning with Renyi Differential Privacy
• dpUGC: Learn Differentially Private Representation for User Generated Contents
• Differentially Private Continual Learning
• DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks
• Deep Learning with Label Differential Privacy
• Improving Robustness to Model Inversion Attacks via Mutual Information Regularization
• Mitigating Sybil Attacks on Differential Privacy based Federated Learning
• Trade-offs and Guarantees of Adversarial Representation Learning for Information Obfuscation
• TextHide: Tackling Data Privacy in Language Understanding Tasks
• Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness
• Differentially Private (Gradient) Expectation Maximization Algorithm with Statistical Guarantees
• Voting-based Approaches For Differentially Private Federated Learning
• Actor Critic with Differentially Private Critic
• Efficient Privacy Preserving Edge Computing Framework for Image Classification
• Where have you been? A Study of Privacy Risk for Point-of-Interest Recommendation
• A Privacy-Preserving Distributed Control of Optimal Power Flow
• Quantum delegated and federated learning via quantum homomorphic encryption
• Privacy Preserving Stochastic Channel-Based Federated Learning with Neural Network Pruning
• Generative Zero-shot Network Quantization
• Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks
• DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
• Differentially Private Synthetic Data Generation Using Context-Aware GANs
• PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
• Communication-Efficient Federated Learning with Compensated Overlap-FedAvg
• Improved Differentially Private Decentralized Source Separation for fMRI Data
• Tight and Robust Private Mean Estimation with Few Users
• On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach
• Differentially Private Bayesian Inference for Generalized Linear Models
• Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach
• Federated Learning in Adversarial Settings
• Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning
• A Blockchain-Based Approach for Saving and Tracking Differential-Privacy Cost
• Differentially Private Deep Learning with Direct Feedback Alignment
• Methods for generating and evaluating synthetic longitudinal patient data: a systematic review
• Shredder: Learning Noise Distributions to Protect Inference Privacy
• Low-Latency Federated Learning over Wireless Channels with Differential Privacy
• Dr.Aid: Supporting Data-governance Rule Compliance for Decentralized Collaboration in an Automated Way
• High Dimensional Model Explanations: an Axiomatic Approach
• Renyi Differential Privacy of the Subsampled Shuffle Model in Distributed Learning
• Duet: An Expressive Higher-order Language and Linear Type System for Statically Enforcing Differential Privacy
• Private Stochastic Convex Optimization: Optimal Rates in ${\ell }_1$ Geometry
• Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification
• Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
• Differentially Private Distributed Computation via Public-Private Communication Networks
• The Differentially Private Lottery Ticket Mechanism
• Efficient Sparse Least Absolute Deviation Regression with Differential Privacy
• Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption
• A Lightweight Privacy-Preserving Scheme Using Label-based Pixel Block Mixing for Image Classification in Deep Learning
• Using Decentralized Aggregation for Federated Learning with Differential Privacy
• Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning
• Label differential privacy via clustering
• Defending Medical Image Diagnostics against Privacy Attacks using Generative Methods
• Private Meeting Summarization Without Performance Loss
• PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization
• Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
• Federated learning with differential privacy and an untrusted aggregator
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Lossless Compression of Efficient Private Local Randomizers
• PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
• Differentially Private Regression and Classification with Sparse Gaussian Processes
• Policy-Based Federated Learning
• Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data
• A Deep Learning Approach to Private Data Sharing of Medical Images Using Conditional GANs
• Machine Unlearning via Algorithmic Stability
• LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation
• Differential Private Stack Generalization with an Application to Diabetes Prediction
• Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling under Data Governance
• Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
• PrivColl: Practical Privacy-Preserving Collaborative Machine Learning
• Generalization Techniques Empirically Outperform Differential Privacy against Membership Inference
• Super-convergence and Differential Privacy: Training faster with better privacy guarantees
• P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model
• Synthetic data shuffling accelerates the convergence of federated learning under data heterogeneity
• Private Multi-Task Learning: Formulation and Applications to Federated Learning
• Data collaboration analysis for distributed datasets
• Bounding, Concentrating, and Truncating: Unifying Privacy Loss Composition for Data Analytics
• Near Instance-Optimality in Differential Privacy
• Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communication
• Robustness Threats of Differential Privacy
• StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting
• Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms
• A Fully Private Pipeline for Deep Learning on Electronic Health Records
• Model Extraction and Defenses on Generative Adversarial Networks
• An Analysis of the Deployment of Models Trained on Private Tabular Synthetic Data: Unexpected Surprises
• Stochastic Adaptive Line Search for Differentially Private Optimization
• Differentially Private Convex Optimization with Feasibility Guarantees
• Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling
• Synthetic Tabular Data: Methods, Attacks and Defenses
• Privacy-preserving Collaborative Learning with Automatic Transformation Search
• Releasing Graph Neural Networks with Differential Privacy Guarantees
• Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?
• Improved Matrix Gaussian Mechanism for Differential Privacy
• Effective and Privacy preserving Tabular Data Synthesizing
• Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data
• Federated Learning for Open Banking
• EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning
• Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
• The Connection between Out-of-Distribution Generalization and Privacy of ML Models
• Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning
• Privacy-Preserving Distributed Zeroth-Order Optimization
• One-Shot Federated Learning with Neuromorphic Processors
• Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT
• Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
• Robust and Private Learning of Halfspaces
• Differentially Private Variational Dropout
• Membership Inference Attacks Against Object Detection Models
• Node-Level Differentially Private Graph Neural Networks
• Public Data-Assisted Mirror Descent for Private Model Training
• On the Privacy Risks of Deploying Recurrent Neural Networks in Machine Learning Models
• DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning
• A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations
• Local Differential Privacy in Decentralized Optimization
• The Trade-Offs of Private Prediction
• Perun: Secure Multi-Stakeholder Machine Learning Framework with GPU Support
• Robustness, Privacy, and Generalization of Adversarial Training
• Privacy-Preserving Collaborative Deep Learning with Unreliable Participants
• Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation
• Assisted Learning for Organizations with Limited Imbalanced Data
• Differentially Private Data Generation with Missing Data
• Survey on AI Ethics: A Socio-technical Perspective
• DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
• P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification
• Decaffe: DHT Tree-Based Online Federated Fake News Detection
• Deep Learning Application in Security and Privacy -- Theory and Practice: A Position Paper
• Towards practical differentially private causal graph discovery
• Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent
• Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)
• Model-based Differentially Private Data Synthesis and Statistical Inference in Multiply Synthetic Differentially Private Data
• SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
• Distributed Optimization for Client-Server Architecture with Negative Gradient Weights
• Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning
• Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT
• Privacy-Preserving Kickstarting Deep Reinforcement Learning with Privacy-Aware Learners
• Differentially Private Decentralized Optimization with Relay Communication
• On the Differential Private Data Market: Endogenous Evolution, Dynamic Pricing, and Incentive Compatibility
• PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy
• Privacy Preserving Conversion Modeling in Data Clean Room
• Federated Unlearning
• Secure Data Sharing With Flow Model
• DP-REC: Private & Communication-Efficient Federated Learning
• GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning
• Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
• Learning to Succeed while Teaching to Fail: Privacy in Closed Machine Learning Systems
• Review learning: Real world validation of privacy preserving continual learning across medical institutions
• Energy cost and machine learning accuracy impact of k-anonymisation and synthetic data techniques
• DPD-InfoGAN: Differentially Private Distributed InfoGAN
• On Large-Cohort Training for Federated Learning
• Optimizing Privacy-Preserving Outsourced Convolutional Neural Network Predictions
• Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
• Trustworthy AI Inference Systems: An Industry Research View
• When Homomorphic Cryptosystem Meets Differential Privacy: Training Machine Learning Classifier with Privacy Protection
• Boosting Model Performance through Differentially Private Model Aggregation
• Disentangling private classes through regularization
• On Connecting Stochastic Gradient MCMC and Differential Privacy
• Accelerating Federated Learning in Heterogeneous Data and Computational Environments
• An Efficient DP-SGD Mechanism for Large Scale NLP Models
• Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
• Memorization of Named Entities in Fine-tuned BERT Models
• DPack: Efficiency-Oriented Privacy Budget Scheduling
• Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data
• A Communication-efficient Local Differentially Private Algorithm in Federated Optimization
• From Private to Public: Benchmarking GANs in the Context of Private Time Series Classification
• Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks
• Can Differential Privacy Practically Protect Collaborative Deep Learning Inference for the Internet of Things?
• Privacy-Preserving Machine Learning in Untrusted Clouds Made Simple
• Trading Data For Learning: Incentive Mechanism For On-Device Federated Learning
• Fuzzi: A Three-Level Logic for Differential Privacy
• Noise Variance Optimization in Differential Privacy: A Game-Theoretic Approach Through Per-Instance Differential Privacy
• Federated Survival Analysis with Discrete-Time Cox Models
• Synthetic Trajectory Generation Through Convolutional Neural Networks
• A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes
• An Empirical Study on the Intrinsic Privacy of SGD
• Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
• Disclosure Risk from Homogeneity Attack in Differentially Private Frequency Distribution
• RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
• Perceptual Indistinguishability-Net (PI-Net): Facial Image Obfuscation with Manipulable Semantics
• Decentralized Differentially Private Without-Replacement Stochastic Gradient Descent
• Optimizing Fitness-For-Use of Differentially Private Linear Queries
• Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning
• Domain Impression: A Source Data Free Domain Adaptation Method
• Federated machine learning with Anonymous Random Hybridization (FeARH) on medical records
• Obfuscation of Images via Differential Privacy: From Facial Images to General Images
• GDRQ: Group-based Distribution Reshaping for Quantization
• Differentially Private Federated Learning via Inexact ADMM
• Privacy Preserving Machine Learning: Threats and Solutions
• Constrained Differentially Private Federated Learning for Low-bandwidth Devices
• When Differential Privacy Meets Interpretability: A Case Study
• Adapting to Function Difficulty and Growth Conditions in Private Optimization
• Correlated Data in Differential Privacy: Definition and Analysis
• Improving Differentially Private Models with Active Learning
• Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation
• Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
• Private Optimization Without Constraint Violations
• Adaptive Differentially Private Empirical Risk Minimization
• DPCOVID: Privacy-Preserving Federated Covid-19 Detection
• Masked LARk: Masked Learning, Aggregation and Reporting worKflow
• Utility-aware Privacy-preserving Data Releasing
• SMAP: A Joint Dimensionality Reduction Scheme for Secure Multi-Party Visualization
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence
• Towards Distributed Privacy-Preserving Prediction
• Reaching Data Confidentiality and Model Accountability on the CalTrain
• Unsupervised Geometric Disentanglement for Surfaces via CFAN-VAE
• An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks
• Communication Efficient Federated Learning with Adaptive Quantization
• Information-constrained optimization: can adaptive processing of gradients help?
• The Influence of Dropout on Membership Inference in Differentially Private Models
• Composable Generative Models
• Gain without Pain: Offsetting DP-injected Nosies Stealthily in Cross-device Federated Learning
• Privacy-preserving Channel Estimation in Cell-free Hybrid Massive MIMO Systems
• A Differentially Private Multi-Output Deep Generative Networks Approach For Activity Diary Synthesis
• Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methods
• SSGD: A safe and efficient method of gradient descent
• AHEAD: Adaptive Hierarchical Decomposition for Range Query under Local Differential Privacy
• Secure Machine Learning over Relational Data
• Do I Get the Privacy I Need? Benchmarking Utility in Differential Privacy Libraries
• Utility Fairness for the Differentially Private Federated Learning
• Data-Free Evaluation of User Contributions in Federated Learning
• Generative Models for Security: Attacks, Defenses, and Opportunities
• TableGAN-MCA: Evaluating Membership Collisions of GAN-Synthesized Tabular Data Releasing
• Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms
• Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
• Oneshot Differentially Private Top-k Selection
• Privately Learning Subspaces
• H-FL: A Hierarchical Communication-Efficient and Privacy-Protected Architecture for Federated Learning
• Detection of Lying Electrical Vehicles in Charging Coordination Application Using Deep Learning
• Exploring the Unfairness of DP-SGD Across Settings
• Median regression with differential privacy
• MetaMorphosis: Task-oriented Privacy Cognizant Feature Generation for Multi-task Learning
• Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models
• Data Poisoning and Leakage Analysis in Federated Learning
• A Human-Centered Privacy Approach (HCP) to AI
• Distributed Deep Learning for Medical Image Denoising with Data Obfuscation
• FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
• LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning
• Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifiers
• Federated Learning With Individualized Privacy Through Client Sampling
• PPVF: An Efficient Privacy-Preserving Online Video Fetching Framework with Correlated Differential Privacy
• Interpretable collaborative data analysis on distributed data
• Inferring Communities of Interest in Collaborative Learning-based Recommender Systems
• Differentially Private Adapters for Parameter Efficient Acoustic Modeling
• From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning
• Towards Differentially Private Text Representations
• Security and Privacy Preserving Deep Learning
• High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent
• Sharper Utility Bounds for Differentially Private Models
• Network Generation with Differential Privacy
• Modelos dinâmicos aplicados à aprendizagem de valores em inteligência artificial
• Task-aware Privacy Preservation for Multi-dimensional Data
• An automatic differentiation system for the age of differential privacy
• Heavy-tailed Streaming Statistical Estimation
• On the Intrinsic Differential Privacy of Bagging
• GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks
• GRAFFL: Gradient-free Federated Learning of a Bayesian Generative Model
• Syft 0.5: A Platform for Universally Deployable Structured Transparency
• D3p -- A Python Package for Differentially-Private Probabilistic Programming
• An Analysis Of Protected Health Information Leakage In Deep-Learning Based De-Identification Algorithms
• Privacy-Preserving Machine Learning Training in Aggregation Scenarios
• Improving Utility of Differentially Private Mechanisms through Cryptography-based Technologies: a Survey
• Privacy-preserving Data Sharing on Vertically Partitioned Data
• Quantifying Membership Privacy via Information Leakage
• Differentially Private Federated Variational Inference
• An Adaptive and Fast Convergent Approach to Differentially Private Deep Learning
• DP-CGAN: Differentially Private Synthetic Data and Label Generation
• Differentially Private M-band Wavelet-Based Mechanisms in Machine Learning Environments
• Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data
• Private Deep Learning with Teacher Ensembles
• Private Hierarchical Clustering and Efficient Approximation
• Free Gap Information from the Differentially Private Sparse Vector and Noisy Max Mechanisms
• Maximal Information Leakage based Privacy Preserving Data Disclosure Mechanisms
• Who started this rumor? Quantifying the natural differential privacy guarantees of gossip protocols
• Do Not Return Similarity: Face Recovery with Distance
• Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
• Corella: A Private Multi Server Learning Approach based on Correlated Queries
• Differentially Private Link Prediction With Protected Connections
• Semi-Federated Learning
• Secure Metric Learning via Differential Pairwise Privacy
• Balance is key: Private median splits yield high-utility random trees
• Topology-aware Differential Privacy for Decentralized Image Classification
• A Graph Symmetrisation Bound on Channel Information Leakage under Blowfish Privacy
• Splintering with distributions: A stochastic decoy scheme for private computation
• Against Membership Inference Attack: Pruning is All You Need
• Amplifying Rényi Differential Privacy via Shuffling
• Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization
• Learning Realistic Patterns from Unrealistic Stimuli: Generalization and Data Anonymization
• Renyi Differentially Private ADMM for Non-Smooth Regularized Optimization
• DuetSGX: Differential Privacy with Secure Hardware
• Confidential Machine Learning on Untrusted Platforms: A Survey
• MYSTIKO : : Cloud-Mediated, Private, Federated Gradient Descent
• Taming Distrust in the Decentralized Internet with PIXIU
• Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
• Protecting Big Data Privacy Using Randomized Tensor Network Decomposition and Dispersed Tensor Computation
• Private Knowledge Transfer via Model Distillation with Generative Adversarial Networks
• Accuracy Gains from Privacy Amplification Through Sampling for Differential Privacy
• NegDL: Privacy-Preserving Deep Learning Based on Negative Database
• Rejoinder: Gaussian Differential Privacy
• Privacy-Preserving Portrait Matting
• PUTWorkbench: Analysing Privacy in AI-intensive Systems
• Gaussian Processes with Differential Privacy
• Community Preserved Social Graph Publishing with Node Differential Privacy
• Differentially Private Densest Subgraph Detection
• Selective Differential Privacy for Language Modeling
• On the Differentially Private Nature of Perturbed Gradient Descent
• Partial sensitivity analysis in differential privacy
• Efficient Private Machine Learning by Differentiable Random Transformations
• A closed form scale bound for the $(\epsilon ,\delta )$-differentially private Gaussian Mechanism valid for all privacy regimes
• Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling
• What Storage Access Privacy is Achievable with Small Overhead?
• One-Bit Matrix Completion with Differential Privacy
• Distributed Layer-Partitioned Training for Privacy-Preserved Deep Learning
• Combining Differential Privacy and Byzantine Resilience in Distributed SGD
• CryptoNite: Revealing the Pitfalls of End-to-End Private Inference at Scale
• DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?
• Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design
• Prior-Independent Auctions for the Demand Side of Federated Learning
• Improving Differentially Private SGD via Randomly Sparsified Gradients
• TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data
• Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems
• Privacy accounting $\epsilon$conomics: Improving differential privacy composition via a posteriori bounds
• Reducing Risk of Model Inversion Using Privacy-Guided Training
• Stability Enhanced Privacy and Applications in Private Stochastic Gradient Descent
• Differentially Private Multivariate Statistics with an Application to Contingency Table Analysis
• BadVFL: Backdoor Attacks in Vertical Federated Learning
• The Relative Gaussian Mechanism and its Application to Private Gradient Descent
• Privately Answering Queries on Skewed Data via Per Record Differential Privacy
• Privacy-Aware Document Visual Question Answering
• IRG: Modular Synthetic Relational Database Generation with Complex Relational Schemas
• Auditing Differential Privacy Guarantees Using Density Estimation
• Local SGD for Near-Quadratic Problems: Improving Convergence under Unconstrained Noise Conditions
• Accelerated Stochastic ExtraGradient: Mixing Hessian and Gradient Similarity to Reduce Communication in Distributed and Federated Learning
• Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery
• DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing
• BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation
• Tensorization of neural networks for improved privacy and interpretability
• FedOptima: Optimizing Resource Utilization in Federated Learning
• A Novel Approach to Differential Privacy with Alpha Divergence
• Robust and Differentially Private Principal Component Analysis
• FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data
• Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education
• A Robust Framework for Secure Cardiovascular Risk Prediction: An Architectural Case Study of Differentially Private Federated Learning
• Towards Efficient and Secure Delivery of Data for Training and Inference with Privacy-Preserving
• SoK: Practical Aspects of Releasing Differentially Private Graphs
• Integrating Homomorphic Encryption and Synthetic Data in FL for Privacy and Learning Quality
• On Privacy Protection of Latent Dirichlet Allocation Model Training
• ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning
• Byzantine-Resilient Federated Machine Learning via Over-the-Air Computation
• Towards Explainable Multi-Party Learning: A Contrastive Knowledge Sharing Framework
• Causally Constrained Data Synthesis for Private Data Release
• On Privacy and Confidentiality of Communications in Organizational Graphs
• Towards Sharper Utility Bounds for Differentially Private Pairwise Learning
• Continuous Latent Process Flows
• Regularized Loss Minimizers with Local Data Perturbation: Consistency and Data Irrecoverability
• A Privacy-Preserving and Trustable Multi-agent Learning Framework
• Privacy Amplification via Iteration for Shuffled and Online PNSGD
• Littlestone Classes are Privately Online Learnable
• Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challenges
• Gradient-Leakage Resilient Federated Learning
• Hierarchical Online Convex Optimization
• Statistical Guarantees for Fairness Aware Plug-In Algorithms
• Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty
• Sometimes You Want to Go Where Everybody Knows your Name
• Multi-Party Dual Learning
• User-centric Composable Services: A New Generation of Personal Data Analytics
• Efficient Hyperparameter Optimization for Differentially Private Deep Learning
• Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques
• Privacy enabled Financial Text Classification using Differential Privacy and Federated Learning
• Flexible Accuracy for Differential Privacy
• A Survey on Threat Situation Awareness Systems: Framework, Techniques, and Insights
• Differentially Private ADMM Algorithms for Machine Learning
• CatFedAvg: Optimising Communication-efficiency and Classification Accuracy in Federated Learning
• Towards Efficient and Secure Delivery of Data for Deep Learning with Privacy-Preserving
• Adversarial Data Encryption
• Not Just Cloud Privacy: Protecting Client Privacy in Teacher-Student Learning
• Privacy-Preserving Bandits
• Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
• Privacy-Preserving Public Release of Datasets for Support Vector Machine Classification
• Differentially Private Generation of Small Images
• Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud
• Bilevel Optimization for Differentially Private Optimization in Energy Systems