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

Noor Islam S. Mohammad

2 indexed papers

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

Publications per year

2
26

Top categories

Crypto×2ML×1

Frequent co-authors

Uluğ Bayazıt1×

Research Timeline

2026
EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection

EdgeDetect is a communication-efficient and privacy-preserving federated intrusion detection system that uses gradient binarization and homomorphic encryption to significantly reduce bandwidth usage while maintaining high detection accuracy.

SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

SafeLM is a comprehensive framework that jointly addresses privacy, security, misinformation, and adversarial robustness in federated LLMs, achieving high safety performance while significantly reducing communication and enhancing privacy.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.LGRecentApr 17, 2026

SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

Noor Islam S. Mohammad, Uluğ Bayazıt

SafeLM is a comprehensive framework that jointly addresses privacy, security, misinformation, and adversarial robustness in federated LLMs, achieving high safety performance while significantly reduci…

View →
cs.CRRecentApr 16, 2026

EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection

Noor Islam S. Mohammad

EdgeDetect is a communication-efficient and privacy-preserving federated intrusion detection system that uses gradient binarization and homomorphic encryption to significantly reduce bandwidth usage w…

View →