AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

Fed-CBE: Client-Side Backdoor Elimination in Federated Learning via Persistent Parameter Disruption

inforesearchPeer-Reviewed

securityresearch

Source: IEEE Xplore (Security & AI Journals)August 12, 2026

Summary

Federated learning (a way to train AI models where data stays on users' devices instead of being sent to a central server) is vulnerable to backdoor attacks (hidden malicious behaviors inserted into models by attackers), which existing defenses cannot fully stop, especially when attackers poison the model over multiple rounds. Researchers propose Fed-CBE, a defense method that uses three techniques: periodically resetting certain model layers, making the model forget incorrect categories using entropy maximization (spreading predictions evenly across wrong answers), and recovering original task performance through knowledge distillation (copying learned knowledge from older model versions), achieving near-zero attack success rates without hurting normal performance.

Solution / Mitigation

The source proposes Fed-CBE as a defense mechanism employing three specific techniques: '1) periodic alternating layer resetting disrupts deep parameters to dismantle cross-round backdoor accumulation; 2) indiscriminate forgetting employs entropy maximization on non-ground-truth classes to decouple backdoor associations without prior trigger knowledge; and 3) knowledge distillation with historical local models restores primary task performance.' The paper reports that this approach achieves 'near-zero levels' attack success rates in most settings while maintaining primary task performance.