Secure Byzantine-Robust Machine Learning

Abstract

Increasingly machine learning systems are being deployed to edge servers and devices (e.g. mobile phones) and trained in a collaborative manner. Such distributed/federated/decentralized training raises a number of concerns about the robustness, privacy, and security of the procedure. While extensive work has been done in tackling with robustness, privacy, or security individually, their combination has rarely been studied. In this paper, we propose a secure two-server protocol that offers both input privacy and Byzantine-robustness. In addition, this protocol is communication-efficient, fault-tolerant and enjoys local differential privacy.

References in corpus (16)

• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Robust Aggregation for Federated Learning
• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• The Hidden Vulnerability of Distributed Learning in Byzantium
• CryptoDL: Deep Neural Networks over Encrypted Data
• Byzantine Stochastic Gradient Descent
• Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging
• XONN: XNOR-based Oblivious Deep Neural Network Inference
• Robust Federated Learning in a Heterogeneous Environment
• Prio: Private, Robust, and Scalable Computation of Aggregate Statistics
• Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
• Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance
• Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation
• Secure Computation for Machine Learning With SPDZ
• Phocas: dimensional Byzantine-resilient stochastic gradient descent

Cited by in corpus (11)

• From Distributed Machine Learning to Federated Learning: A Survey
• A Field Guide to Federated Optimization
• FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
• Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
• Robust Aggregation for Adaptive Privacy Preserving Federated Learning in Healthcare
• Byzantine-Resilient Secure Federated Learning
• PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy
• Secure Byzantine-Robust Distributed Learning via Clustering
• A Survey on Fault-tolerance in Distributed Optimization and Machine Learning
• Federated learning with differential privacy and an untrusted aggregator
• Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?