Honest Score Client Selection Scheme: Preventing Federated Learning Label Flipping Attacks in Non-IID Scenarios. (arXiv:2311.05826v1 [cs.CR])

Federated Learning (FL) is a promising technology that enables multiple
actors to build a joint model without sharing their raw data. The distributed
nature makes FL vulnerable to various poisoning attacks, including model
poisoning attacks and data poisoning attacks. Today, many byzantine-resilient
FL methods have been introduced to mitigate the model poisoning attack, while
the effectiveness when defending against data poisoning attacks still remains
unclear. In this paper, we focus on the most representative data poisoning
attack - "label flipping …

attacks build client data data poisoning distributed federated federated learning nature non poisoning poisoning attacks score sharing technology today vulnerable