Md. Nahid Hasan

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Eval Frameworks & Benchmarks (1)Red-Teaming & Adversarial Robustness (1)Data Curation & Synthetic Data (1)Distributed Systems & Hardware (1)

Frequent co-authors

M. N. Hasan (1)Golam Rabiul Alam (1)

Papers (2)

Aug 11, 2026

Md. Nahid Hasan2w ago

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs

Self-feeding can detect backdoors in fine-tuned LLMs with 92% precision, outperforming traditional methods and revealing hidden vulnerabilities in models that appear safe.

Md. Nahid Hasan

Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Jul 8, 2026

M. N. Hasan +2Jul 8, 2026

Unlearning to Protect: A Distilled Reinforcement Learning Framework with Privacy-Preserving Feature Unlearning and XAI for IoT Security

Achieving 99.60% accuracy with a model that requires only 2,370 FLOPS could redefine the landscape of IoT security solutions.

M. N. Hasan, Md. Nahid Hasan, Golam Rabiul Alam

Data Curation & Synthetic Data Distributed Systems & Hardware Interpretability & Mechanistic Interp+1

Search

Md. Nahid Hasan

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)