Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
This paper addresses the problem of combining Byzantine resilience with privacy in machine learning (ML). Specifically, we study if a distributed implementation of the renowned Stochastic Gradient Descent (SGD) learning algorithm is feasible with both differential privacy (DP) and $(\alpha,f)$-Byzantine resilience. To the best of our knowledge, this is the first work to tackle this problem from a theoretical point of view. A key finding of our analyses is that the classical approaches to these two (seemingly) orthogonal issues are incompatible. More precisely, we show that a direct composition of these techniques makes the guarantees of the resulting SGD algorithm depend unfavourably upon the number of parameters of the ML model, making the training of large models practically infeasible. We validate our theoretical results through numerical experiments on publicly-available datasets; showing that it is impractical to ensure DP and Byzantine resilience simultaneously.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Practical Differentially Private and Byzantine-resilient Federated Learning
Privacy and Byzantine resilience are two indispensable requirements for a federated learning (FL) system. Although there have been extensive studies on privacy and Byzantine security in their own track, solutions that co…
Federated LearningPrivacy PreservingTernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data
Distributed training of deep neural networks faces three critical challenges: privacy preservation, communication efficiency, and robustness to fault and adversarial behaviors. Although significant research efforts have …
Distributed OptimizationCombining Differential Privacy and Byzantine Resilience in Distributed SGD
Privacy and Byzantine resilience (BR) are two crucial requirements of modern-day distributed machine learning. The two concepts have been extensively studied individually but the question of how to combine them effective…
Hyperparameter OptimizationPerfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learning
Federated learning (FL) shows great promise in large-scale machine learning but introduces new privacy and security challenges. We propose ByITFL and LoByITFL, two novel FL schemes that enhance resilience against Byzanti…
Federated LearningByzantine-Robust Federated Learning with Variance Reduction and Differential Privacy
Federated learning (FL) is designed to preserve data privacy during model training, where the data remains on the client side (i.e., IoT devices), and only model updates of clients are shared iteratively for collaborativ…
Federated Learning