Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks
Kavindu Herath, Joshua C. Zhao, Saurabh Bagchi
Federated learning is vulnerable to backdoor attacks in which malicious clients inject poisoned updates while preserving benign-task performance. In this paper, we study a semantic…
cs.CR2026
Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learning
Kavindu Herath, Joshua Zhao, Saurabh Bagchi
Backdoor attacks on federated learning (FL) are most often evaluated with synthetic corner patches or out-of-distribution (OOD) patterns that are unlikely to arise in practice. In…