Yuanxiang Wu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1ML×1
Frequent co-authors
Research Timeline
2026
FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
FedSurrogate introduces a novel backdoor defense for Federated Learning that uses layer-criticality analysis and surrogate replacement to significantly reduce false positives while maintaining high model accuracy against malicious clients.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.LGRecentMay 11, 2026
FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
Fatima Z. Abacha, Sin G. Teo, Yuanxiang Wu, Lucas C. Cordeiro +1 more
FedSurrogate introduces a novel backdoor defense for Federated Learning that uses layer-criticality analysis and surrogate replacement to significantly reduce false positives while maintaining high mo…
View →