I am a PhD student in DSA Thrust of the Information Hub at Hong Kong University of Science and Technology (Guangzhou) advised by Prof. Xinlei He.
My research interest includes AI Security and Privacy. (
🔥 News
- 2025.3: 🎉🎉 PEFTGuard got accepted in IEEE S$\&$P 2025
- 2024.11: 🎉🎉 Our paper won the Best Paper Award of SENSYS-SocialMeta’24.
- 2024.06: 🎉🎉 I receive my firm PhD offer from HKUST(GZ).
📝 Publications
$^\star$: Equal contribution; $^\dagger$: Corresponding author
Conference
-
[IEEE S$\&$P’25] PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning
Zhen Sun, Tianshuo Cong, Yule Liu, Chenhao Lin, Xinlei He, Rongmao Chen, Xingshuo Han, and Xinyi Huang.
CCF-A[arxiv] (AR: 257/1740=14.8%, Cycle 2 AR: 151/1001=15.1%) -
[SENSYS-SocialMeta’24] AdSpectorX: A Multimodal Expert Spector for Covert Advertising Detection on Chinese Social Media
Zongmin Zhang, Yujie Han, Zhou Zhang, Yule Liu, Jingyi Zheng, and Zhen Sun$^\dagger$.
In Proceedings of the Third International Workshop on Social and Metaverse Computing, Sensing and Networking, pp. 50-56. 2024.
CCF-B[code] 🏆 Best Paper Award
Under Review $\&$ Manuscript
-
Jailbreak Attacks and Defenses Against Large Language Models: A Survey [arxiv]
Sibo Yi$^\star$, Yule Liu$^\star$, Zhen Sun$^\star$, Tianshuo Cong, Xinlei He, Jiaxing Song, Ke Xu, and Qi Li.
-
Quantized Delta Weight Is Safety Keeper [arxiv]
Yule Liu, Zhen Sun, Xinlei He, and Xinyi Huang
-
On the Generalization Ability of Machine-Generated Text Detectors[arxiv]
Yule Liu, Zhiyuan Zhong, Yifan Liao, Zhen Sun, Jingyi Zheng, Jiaheng Wei, Qingyuan Gong, Fenghua Tong, Yang Chen, Yang Zhang, Xinlei He
-
Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media[arxiv]
Zhen Sun$^\star$, Zongmin Zhang$^\star$, Xinyue Shen, Ziyi Zhang, Yule Liu, Michael Backes, Yang Zhang, Xinlei He
-
FC-Attack: Jailbreaking Large Vision-Language Models via Auto-Generated Flowcharts[arxiv]
Ziyi Zhang$^\star$, Zhen Sun$^\star$, Zongmin Zhang, Jihui Guo, Xinlei He
-
The Rising Threat to Emerging AI-Powered Search Engines[arxiv]
Zeren Luo, Zifan Peng, Yule Liu, Zhen Sun, Mingchen Li, Jingyi Zheng, Xinlei He
👨🎓Services
Reviewer of Conference
- ICML
- CVPR
- SaTML
- EuroS$\&$P
- AsiaCCS
- AAAI
Reviewer of Journals
- IEEE Transactions on Dependable and Secure Computing (TDSC)
- ACM Transactions on Privacy and Security (TOPS)
🥇 Honors and Awards
- 🥈Kaggle Competitions Expert (Vincent Sirius)
- 2020.04, MCM/ICM Meritorious Winner
- 2019 / 2020 / 2021, Third-class Scholarship of BUPT
- 2019 / 2020 / 2021, Excellent Student Leader of BUPT
🎓 Educations
- 2024.08-now, PhD in Data Science Analysis, Hong Kong University of Science and Technology (Guangzhou)
- 2022.08-2023.10, MSc in Computer Science, City University of Hong Kong
- 2018.09-2022.07, BSc in Computer Science and Technology, Beijing University of Posts and Telecommunications
💻 Experiences
-
[Research Assistant] 2023.06 - 2024.05, Centre for Artificial Intelligence and Robotics (CAIR) Hong Kong Institute of Science $\&$ Innovation, Chinese Academy of Sciences (HKISI-CAS) - Surgical LLM and Image Segmentation, Supervisor: Dr. Jinlin Wu and Dr. Zhen Chen
-
[Project Participant] 2022.09-2023.08, City University of Hong Kong - Financial Machine Translation, Supervisor: Prof. Linqi Song