paper-with-me

홈 › Papers

Combining Differential Privacy and Byzantine Resilience in Distributed SGD

2021-10-08 · Rachid Guerraoui, Nirupam Gupta, Rafael Pinot, Sebastien Rouault, John Stephan

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 effectively remains unanswered. This paper contributes to addressing this question by studying the extent to which the distributed SGD algorithm, in the standard parameter-server architecture, can learn an accurate model despite (a) a fraction of the workers being malicious (Byzantine), and (b) the other fraction, whilst being honest, providing noisy information to the server to ensure differential privacy (DP). We first observe that the integration of standard practices in DP and BR is not straightforward. In fact, we show that many existing results on the convergence of distributed SGD under Byzantine faults, especially those relying on $(\alpha,f)$-Byzantine resilience, are rendered invalid when honest workers enforce DP. To circumvent this shortcoming, we revisit the theory of $(\alpha,f)$-BR to obtain an approximate convergence guarantee. Our analysis provides key insights on how to improve this guarantee through hyperparameter optimization. Essentially, our theoretical and empirical results show that (1) an imprudent combination of standard approaches to DP and BR might be fruitless, but (2) by carefully re-tuning the learning algorithm, we can obtain reasonable learning accuracy while simultaneously guaranteeing DP and BR.

📄 PDF Abstract BibTeX arXiv:2110.03991

Code (0)

등록된 구현이 없습니다.

Tasks

Hyperparameter Optimization

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?

2021-02-16 · Rachid Guerraoui, Nirupam Gupta, Rafaël Pinot, Sébastien Rouault 외

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 …

TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data

2024-02-16 · Richeng Jin, Yujie Gu, Kai Yue, Xiaofan He 외

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 Optimization

Practical Differentially Private and Byzantine-resilient Federated Learning

2023-04-15 · Zihang Xiang, Tianhao Wang, WanYu Lin, Di Wang

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 Preserving

Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learning

2025-06-16 · Yue Xia, Christoph Hofmeister, Maximilian Egger, Rawad Bitar

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 Learning

Cellular Traffic Prediction via Byzantine-robust Asynchronous Federated Learning

2025-05-25 · Hui Ma, Kai Yang, Yang Jiao

Network traffic prediction plays a crucial role in intelligent network operation. Traditional prediction methods often rely on centralized training, necessitating the transfer of vast amounts of traffic data to a central…

Federated LearningPredictionPrivacy PreservingTraffic Prediction