AI safety researcher

Weiming Zhang

University of Science and Technology of China

Google Scholar dblp ORCID

Last 12 months14 papers

Attacks 3Interpretability 1

AI safety papers from the last year

On this site: 76 papers

September 2026

The Safeguard Worked. Is the LLM System Safer?
Sep 1arXiv ↗

August 2026

July 2026

Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
Jul 30arXiv ↗
FARI: Robust One-Step Inversion for Watermarking in Diffusion Models
Jul 29arXiv ↗
Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models
Jul 19arXiv ↗

May 2026

Provably Secure Agent Guardrail
May 28arXiv ↗

April 2026

March 2026

State-Dependent Safety Failures in Multi-Turn Language Model Interaction
Mar 15AttacksarXiv ↗

January 2026

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