Zhen Sun
Scholar

Zhen Sun

Google Scholar ID: 7ir2zYsAAAAJ
DSA Thrust, HKUST(GZ)
LLM security
Citations & Impact
All-time
Citations
247
 
H-index
6
 
i10-index
4
 
Publications
18
 
Co-authors
14
list available
Resume (English only)
Academic Achievements
  • Publications:
  • - FC-Attack: Jailbreaking Large Vision-Language Models via Auto-Generated Flowcharts (EMNLP Findings 2025)
  • - Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search (USENIX Security 2025)
  • - Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media (ACL Main 2025)
  • - PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning (IEEE S&P 2025)
  • - On the Generalization Ability of Machine-Generated Text Detectors (KDD D&B 2025)
  • - TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors (KDD D&B 2025)
  • - AdSpectorX: A Multimodal Expert Spector for Covert Advertising Detection on Chinese Social Media (SENSYS-SocialMeta 2024, Best Paper Award)
  • Awards:
  • - Best Paper Award at SENSYS-SocialMeta 2024
  • - Kaggle Competitions Expert
  • - MCM/ICM Meritorious Winner (2020.04)
  • - Third-class Scholarship of BUPT (2019/2020/2021)
  • - Excellent Student Leader of BUPT (2019/2020/2021)
Background
  • PhD student in Data Science Analysis at The Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Xinlei He. Research interests include AI Security and Privacy.
Miscellany
  • Reviewer for multiple international conferences and journals, including ICML, CVPR, SaTML, EuroS&P, AsiaCCS, AAAI, MM, IEEE Transactions on Dependable and Secure Computing (TDSC), and ACM Transactions on Privacy and Security (TOPS).