A generic framework for privacy preserving deep learning

Abstract

We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs such as Federated Learning, Secure Multiparty Computation, and Differential Privacy while still exposing a familiar deep learning API to the end-user. We report early results on the Boston Housing and Pima Indian Diabetes datasets. While the privacy features apart from Differential Privacy do not impact the prediction accuracy, the current implementation of the framework introduces a significant overhead in performance, which will be addressed at a later stage of the development. We believe this work is an important milestone introducing the first reliable, general framework for privacy preserving deep learning.

PPML 2018, 5 pages

Cited by in corpus (87)

• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
• From Distributed Machine Learning to Federated Learning: A Survey
• FedML: A Research Library and Benchmark for Federated Machine Learning
• FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
• HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning
• Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
• Technology Readiness Levels for Machine Learning Systems
• A Field Guide to Federated Optimization
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• IBM Federated Learning: an Enterprise Framework White Paper V0.1
• Privacy-preserving Artificial Intelligence Techniques in Biomedicine
• Flower: A Friendly Federated Learning Research Framework
• FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
• A Review of Anonymization for Healthcare Data
• Towards Efficient and Stable K-Asynchronous Federated Learning with Unbounded Stale Gradients on Non-IID Data
• Real-World Image Datasets for Federated Learning
• Federated Learning for Healthcare Informatics
• FedLab: A Flexible Federated Learning Framework
• PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN
• CrypTen: Secure Multi-Party Computation Meets Machine Learning
• Stratified cross-validation for unbiased and privacy-preserving federated learning
• Security and Privacy Issues in Deep Learning
• Data Poisoning Attacks Against Federated Learning Systems
• A blockchain-orchestrated Federated Learning architecture for healthcare consortia
• Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach
• Towards Communication-efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things
• Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
• Federated Learning with Nesterov Accelerated Gradient
• Federated Learning for Big Data: A Survey on Opportunities, Applications, and Future Directions
• FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
• FLASHE: Additively Symmetric Homomorphic Encryption for Cross-Silo Federated Learning
• SEALion: a Framework for Neural Network Inference on Encrypted Data
• Fed-Focal Loss for imbalanced data classification in Federated Learning
• Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
• Hierarchical Federated Learning through LAN-WAN Orchestration
• Enabling Homomorphically Encrypted Inference for Large DNN Models
• Practical Defences Against Model Inversion Attacks for Split Neural Networks
• SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labeling
• GFL: A Decentralized Federated Learning Framework Based On Blockchain
• Asymmetric Private Set Intersection with Applications to Contact Tracing and Private Vertical Federated Machine Learning
• FedEval: A Holistic Evaluation Framework for Federated Learning
• FedJAX: Federated learning simulation with JAX
• SPEED: Secure, PrivatE, and Efficient Deep learning
• Self-supervised Cross-silo Federated Neural Architecture Search
• Fast-adapting and Privacy-preserving Federated Recommender System
• nGraph-HE: A Graph Compiler for Deep Learning on Homomorphically Encrypted Data
• CaRENets: Compact and Resource-Efficient CNN for Homomorphic Inference on Encrypted Medical Images
• FedBoosting: Federated Learning with Gradient Protected Boosting for Text Recognition
• Partially Encrypted Machine Learning using Functional Encryption
• On the Impact of Device and Behavioral Heterogeneity in Federated Learning
• Secure Quantized Training for Deep Learning
• Federated Learning System without Model Sharing through Integration of Dimensional Reduced Data Representations
• Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data
• 2CP: Decentralized Protocols to Transparently Evaluate Contributivity in Blockchain Federated Learning Environments
• Collaborative City Digital Twin For Covid-19 Pandemic: A Federated Learning Solution
• The More, the Better? A Study on Collaborative Machine Learning for DGA Detection
• DistFL: Distribution-aware Federated Learning for Mobile Scenarios
• Privacy-Preserving Distributed Learning Framework for 6G Telecom Ecosystems
• Privacy-preserving medical image analysis
• SoK: Training Machine Learning Models over Multiple Sources with Privacy Preservation
• A Framework for Democratizing AI
• Privacy-preserving Decentralized Aggregation for Federated Learning
• Secure Medical Image Analysis with CrypTFlow
• PPCA: Privacy-preserving Principal Component Analysis Using Secure Multiparty Computation(MPC)
• Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent
• A Framework for testing Federated Learning algorithms using an edge-like environment
• Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
• WAFFLE: Watermarking in Federated Learning
• A Deep Learning Approach to Private Data Sharing of Medical Images Using Conditional GANs
• PrivColl: Practical Privacy-Preserving Collaborative Machine Learning
• A Lightweight Privacy-Preserving Scheme Using Label-based Pixel Block Mixing for Image Classification in Deep Learning
• Hydra: A Peer to Peer Distributed Training & Data Collection Framework
• A brief history on Homomorphic learning: A privacy-focused approach to machine learning
• Reliability and Performance Assessment of Federated Learning on Clinical Benchmark Data
• Privacy Threats Analysis to Secure Federated Learning
• EasyFL: A Low-code Federated Learning Platform For Dummies
• TiFL: A Tier-based Federated Learning System
• On-device Federated Learning with Flower
• Monte Carlo execution time estimation for Privacy-preserving Distributed Function Evaluation protocols
• Private Dataset Generation Using Privacy Preserving Collaborative Learning
• Flatee: Federated Learning Across Trusted Execution Environments
• The FeatureCloud AI Store for Federated Learning in Biomedicine and Beyond
• Privacy Preserving K-Means Clustering: A Secure Multi-Party Computation Approach
• SIRNN: A Math Library for Secure RNN Inference
• Robust Federated Learning by Mixture of Experts
• NegDL: Privacy-Preserving Deep Learning Based on Negative Database