Osama Wehbi
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes FL-PBM, a novel pre-training defense mechanism for federated learning that proactively filters poisoned data using a multi-stage process, significantly reducing backdoor attack success rates while maintaining high model accuracy.
The paper proposes FedBBA, a robust defense mechanism combining reputation systems, incentive mechanisms, and PPA-based game theory, to significantly mitigate backdoor attacks in Federated Learning.
Papers
FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning
The paper proposes FL-PBM, a novel pre-training defense mechanism for federated learning that proactively filters poisoned data using a multi-stage process, significantly reducing backdoor attack succ…