Scholar
Zhenhong Zhou
Google Scholar ID: 6TuPwzMAAAAJ
Nanyang Technological University
Large Language Model
AI Safety
LLM Safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
248
H-index
8
i10-index
7
Publications
19
Co-authors
0
Contact
Email
zhouzhenhong@bupt.edu.cn
Twitter
Open ↗
GitHub
Open ↗
Publications
31 items
SafeSeek: Universal Attribution of Safety Circuits in Language Models
2026
Cited
0
Resource Consumption Threats in Large Language Models
2026
Cited
0
MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents
2026
Cited
0
Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
2026
Cited
0
RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflection
2026
Cited
0
From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
2026
Cited
0
RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios
2026
Cited
0
SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models
2026
Cited
0
Load more
Resume (English only)
Academic Achievements
ICLR 2025 (Oral, Top 1.8%): 'On the Role of Attention Heads in Large Language Model Safety'
ICML 2025: Paper accepted
ACL 2025: Paper accepted
EMNLP 2024: Two papers accepted, one as co-first author
AAAI 2024: 'Quantifying and Analyzing Entity-Level Memorization in Large Language Models'
arXiv preprint: 'Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue'
Oct 2023: First-class Postgraduate Academic Scholarship, Beijing University of Posts and Telecommunications
Oct 2022: Second-class Postgraduate Academic Scholarship, Beijing University of Posts and Telecommunications
Co-authors
0 total
Co-authors: 0 (list not available)
×
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