2 papers
cs.LG2023
A Huber Loss Minimization Approach to Byzantine Robust Federated Learning
Puning Zhao, Fei Yu, Zhiguo Wan
Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive the…
cs.LG2023
High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers
Wenyu Liu, Tianqiang Huang, Pengfei Zhang +3
Adversarial attacks pose a major challenge to distributed learning systems, prompting the development of numerous robust learning methods. However, most existing approaches suffer…