AI safety researcher

Zhibo Wang

Zhejiang University

Google Scholar dblp ORCID

Last 12 months7 papers

Attacks 2Defenses 1

AI safety papers from the last year

On this site: 29 papers

August 2026

Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference
Aug 2arXiv ↗

July 2026

From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs
Jul 28AttacksarXiv ↗

May 2026

RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
May 24arXiv ↗
LoopTrap: Termination Poisoning Attacks on LLM Agents
May 7AttacksarXiv ↗

March 2026

DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern
Mar 2arXiv ↗

January 2026

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