1. SoK: Evaluating Jailbreak Guardrails for Large Language Models, IEEE Symposium on Security and Privacy (S&P), 2026
2. SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner, USENIX Security Symposium (USENIX Security), 2025
3. Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval, IEEE Transactions on Information Forensics and Security (TIFS), 2023
4. CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrieval, The Web Conference (WWW), 2023
5. Targeted Attack of Deep Hashing via Prototype-Supervised Adversarial Networks, IEEE Transactions on Multimedia (TMM), 2022
6. Targeted Attack and Defense for Deep Hashing, ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2021
7. Prototype-Supervised Adversarial Network for Targeted Attack of Deep Hashing, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Preprints:
1. STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models, arXiv, 2025
2. GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods, arXiv, 2025
3. InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models, arXiv, 2023
Honors:
- Outstanding Master's Thesis Award by the Chinese Institute of Electronics, 2023
- HKUST RedBird PhD Scholarship, 2022
- Outstanding Master's Thesis Award by Harbin Institute of Technology, 2022
- National Scholarship, 2021
- National Encouragement Scholarship, 2017
- National Encouragement Scholarship, 2016
Research Experience
No specific work experience or research projects mentioned.
Education
1. Ph.D. student in the Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, advised by Prof. Shuai Wang.
2. M.Eng. from Harbin Institute of Technology (Shenzhen), graduated in January 2022, advised by Prof. Zheng Zhang.
3. B.Eng. from China University of Geosciences, Wuhan, graduated in 2019.
Background
Research interests: AI Safety & Security, LLM Security, Adversarial Machine Learning.