Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Osama Wehbi

Osama Wehbi

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×2Crypto×2Distributed×2Game Theory×1

Frequent co-authors

Sarhad Arisdakessian2×
Omar Abdel Wahab2×
Azzam Mourad2×
Hadi Otrok2×
Jamal Bentahar1×
Anderson Avila1×

Research Timeline

2026
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 success rates while maintaining high model accuracy.

Mitigating Backdoor Attacks in Federated Learning Using PPA and MiniMax Game Theory

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.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CRcs.DCRecentMar 30, 2026

FL-PBM: Pre-Training Backdoor Mitigation for Federated Learning

Osama Wehbi, Sarhad Arisdakessian, Omar Abdel Wahab, Azzam Mourad +2 more

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…

View →
cs.LGcs.CRcs.DCRecentMar 30, 2026

Mitigating Backdoor Attacks in Federated Learning Using PPA and MiniMax Game Theory

Osama Wehbi, Sarhad Arisdakessian, Omar Abdel Wahab, Anderson Avila +2 more

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.

View →