Research & Publications.

Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing

Israt Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Jakir Hossain, M. F. Mridha

arXiv:2608.21423

Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity

Chinmoy Mitra, Md Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md Rakibul Islam, MF Mridha

arXiv:2608.04045

ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria, Tasfia Nuzhat Ornee, Maleeha Sheikh

arXiv:2607.19430

NEXUS: Structured Runtime Safety for Tool-Using LLM Agents

Elias Hossain, Md Mehedi Hasan Nipu, Tasfia Nuzhat Ornee, Rajib Rana, Niloofar Yousefi

The 5th Asia-Pacific Chapter of the Association for Computational Linguistics & the 15th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2026)

ICORE/CORE Rank: B

Safe and Scalable Collaboration in Multiagent LLM Systems: A Comprehensive Review

IEEE Transactions on Systems, Man, and Cybernetics: Systems

Q1, IF: 8.7

From Pixels to Pathology: The Power of CNNs in Detecting Tuberculosis

EAI Endorsed Transactions on Pervasive Health and Technology

MedBayes-Lite: Bayesian Uncertainty Quantification for Safe Clinical Decision Support

arXiv preprint 2511.16625

A Federated and Explainable Machine Learning Framework for Robust Intrusion Detection in IIoT Environments

5th International Conference on Electrical, Computer & Telecommunication Engineering

Enhancing Lung Cancer Detection with Attention Mechanisms and Unified Ensemble Learning

35th International Conference on Computer Theory and Applications

Deep Learning-Based Classification of Rice Varieties for Agricultural Applications

IEEE ARIIA 2024

EchoCardio-FMC-718: An Annotated Echocardiogram Report Dataset

Mendeley Data

Ben-Misandry-5000: An Annotated Bengali Misandry Dataset

Mendeley Data