AI safety researcher

Muhao Chen

Google Scholar dblp OpenReview ORCID Homepage

Last 12 months7 papers

Risky behavior 1Evaluation and benchmarks 1Attacks 1

AI safety papers from the last year

On this site: 39 papers

September 2026

Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time
Sep 26Risky behaviorarXiv ↗

May 2026

April 2026

Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models
Apr 1Evaluation and benchmarksarXiv ↗

January 2026

ReasoningBomb: A Stealthy Denial-of-Service Attack by Inducing Pathologically Long Reasoning in Large Reasoning Models
Jan 29AttacksarXiv ↗

December 2025

OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
Dec 2arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.