3 papers
cs.CR2026
ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria +2
Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel through which an adversary can sm…
cs.LG2026
MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion
Tasfia Nuzhat Ornee, Elias Hossain, Ivan Garibay +1
Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence representation, implicitly tr…
cs.AI2026
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…