Scholar
Hongwei Yao
Google Scholar ID: gjMTPgkAAAAJ
Postdoctoral Fellow at City University of Hong Kong
Trustworthy AI
LLM Security and Safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
326
H-index
7
i10-index
5
Publications
20
Co-authors
7
list available
Contact
No contact links provided.
Publications
11 items
AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
2026
Cited
0
Black-Box Guardrail Reverse-engineering Attack
2025
Cited
0
Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
2025
Cited
0
PromptCOS: Towards System Prompt Copyright Auditing for LLMs via Content-level Output Similarity
2025
Cited
0
SoK: Large Language Model Copyright Auditing via Fingerprinting
2025
Cited
0
Quantifying Conversation Drift in MCP via Latent Polytope
2025
Cited
0
BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
2025
Cited
0
ControlNET: A Firewall for RAG-based LLM System
2025
Cited
0
Load more
Resume (English only)
Co-authors
7 total
Kui Ren
Professor and Dean of Computer Science, Zhejiang University, ACM/IEEE Fellow
Shuo Shao
Zhejiang University
Tong Qiao
Associate Professor, School of Cyberspace, Hangzhou Dianzi University
Yiling He
Research Fellow @University College London; PhD @Zhejiang University
Feng Lin
Zhejiang University
Zhan Qin
Researcher, Zhejiang University
Cong Wang
Department of Computer Science, City University of Hong Kong
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up