Secure Federated Learning Based on the OPTICS Clustering Algorithm and Client Selection
Abstract In Federated Learning (FL), the aggregation servers inevitably face attacks from malicious clients because they cannot directly constrain the behaviour of clients. Effectively detecting and mitigating the impact of these malicious clients on the global model is a critical challenge. This paper proposes a secur...
Chunmei Ma, Zhengyang Zhang, Baogui Huang et al.
· Tsinghua Science & Technolog... · 0 citations