AI safety researcher

Shutao Xia

Google Scholar dblp

Last 12 months11 papers

Attacks 1

AI safety papers from the last year

On this site: 76 papers

June 2026

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment
Jun 13arXiv ↗
MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents
Jun 9AttacksarXiv ↗
Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization
Jun 6arXiv ↗

May 2026

April 2026

November 2025

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