BadCleaner: Defending Backdoor Attacks in Federated Learning via Attention-Based Multi-Teacher Distillation
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Dependable and Secure Computing"
DOI: 10.1109/tdsc.2024.3354049
Abstract: As a privacy-preserving distributed learning paradigm, federated learning (FL) has been proven to be vulnerable to various attacks, among which backdoor attack is one of the toughest. In this attack, malicious users attempt to embed… read more here.
Keywords: multi teacher; attention; via attention; federated learning ... See more keywords