3 papers
cs.CR2026
FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
Fatima Z. Abacha, Sin G. Teo, Yuanxiang Wu +2
Federated Learning remains highly susceptible to backdoor attacks--malicious clients inject targeted behaviours into the global model. Existing defenses suffer from substantial fal…
cs.LG2026
Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
Chibueze Peace Obioma, Youcheng Sun, Mustafa A. Mustafa
Federated learning (FL) remains highly vulnerable to adaptive backdoor attacks that preserve stealth by closely imitating benign update statistics. Existing defenses predominantly…
cs.SE2026
Specification Vibing for Automated Program Repair
Taohong Zhu, Lucas C. Cordeiro, Mustafa A. Mustafa +1
Large language model (LLM)-driven automated program repair (APR) has advanced rapidly, but most methods remain code-centric: they directly rewrite source code and thereby risk hall…