AI safety researcher

Chao Shen

Google Scholar dblp OpenReview ORCID

Last 12 months16 papers

Evaluation and benchmarks 3

AI safety papers from the last year

On this site: 68 papers

August 2026

MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration
Aug 6arXiv ↗

July 2026

Alignment Is Local: A Paired Diagnostic for GUI Agents under User-Side Persuasion
Jul 31arXiv ↗
On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline
Jul 16arXiv ↗

June 2026

VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models
Jun 10arXiv ↗
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
Jun 1Evaluation and benchmarksarXiv ↗

May 2026

CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection
May 1arXiv ↗

April 2026

March 2026

When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
Mar 25arXiv ↗

January 2026

False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models
Jan 12Evaluation and benchmarksarXiv ↗

December 2025

Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
Dec 8arXiv ↗

November 2025

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