6 papers
Ben-Misandry: A Bengali Dataset and Late-Fusion Transformer Framework for Detecting Anti-Male Gender Hate
Md Mehedi Hasan Nipu, Chinmoy Mitra, Tarannum Ahmed Nowshin +1
Gender based hate speech research in Bengali has focused almost exclusively on misogyny, leaving anti male hate, or misandry, entirely unstudied for this language and creating a sy…
Trust-Gated Capability Control: Breaking the Trust-Vulnerability Paradox in Multi-Agent LLM Systems
Mehedi Hasan Nipu, Chinmoy Mitra, Tarannum Ahmed Nowshin +1
Layered trust models for multi-agent LLM systems remain largely conceptual: they name which dimensions of trust matter but not how layers combine, how their importance is set at ru…
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 +3
Agentic security uses large-language-model (LLM) agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to deployed products, practitione…
ChannelGuard: From Borrowed Safety to Application-Controlled Defenses in Multi-Agent LLMs
Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria +4
AI assistants increasingly work as teams, where one model makes a plan, others search the web, use tools, or read stored information, and another writes the final answer. This crea…
NEXUS: Structured Runtime Safety for Tool-Using LLM Agents
Elias Hossain, Md Mehedi Hasan Nipu, Tasfia Nuzhat Ornee +2
Tool-using LLM agents increasingly execute high-impact actions, making runtime safety monitoring essential. We present NEXUS (Neural EXecution Utility and Safety), a structured-pla…
MedBayes-Lite: A Clinical Uncertainty Governance Layer for Risk-Aware Medical Decision Support
Elias Hossain, Md Mehedi Hasan Nipu, Maleeha Sheikh +5
Clinical language models often assign high confidence to incorrect predictions, particularly in high-severity and out-of-distribution cases. We present MedBayes-Lite, a retraining-…