About Me
I am a last-year Ph.D. student at Zhejiang University, supervised by Prof. Wenzhi Chen and Prof. Chengkun Wei. I am currently a Visiting Graduate Researcher (VGR) at the University of Virginia, advised by Prof. Tianhao Wang. I got my Bachelor’s degree from Huazhong University of Science and Technology. I have long in-depth research experience in LLM security and privacy and is the second one in Mainland China who won NDSS Distinguished Paper Award (the first in the field of LLM security).
I am looking to pursue a career in industry and am actively seeking job opportunities. Please feel free to contact me if you have any relevant positions or would like to connect!
Research Interests
LLM Privacy and Security
News
Our paper Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation has been accepted by IEEE Transactions on Information Forensics and Security!
Publications
Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation
Wenlong Meng, Fan Zhang, Wendao Yao, Zhenyuan Guo, Yuwei Li, Chengkun Wei, Wenzhi Chen; T-IFS 2026 [PDF] [Code]
Enhancing Meme Emotion Understanding with Multi-Level Modality Enhancement and Dual-Stage Modal Fusion
Yi Shi, Wenlong Meng, Zhenyuan Guo, Chengkun Wei, Wenzhi Chen; AAAI 2026 [PDF] [Code]
Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
Yan Pang, Wenlong Meng, Xiaojing Liao, Tianhao Wang; NDSS 2026 [PDF] [Code]
GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors
Wenlong Meng, Shuguo Fan, Chengkun Wei, Min Chen, Yuwei Li, Yuanchao Zhang, Zhikun Zhang, Wenzhi Chen; USENIX Security 2025 [PDF] [Code]
R.R.: Unveiling LLM Training Privacy through Recollection and Ranking
Wenlong Meng, Zhenyuan Guo, Lenan Wu, Chen Gong, Wenyan Liu, Weixian Li, Chengkun Wei, Wenzhi Chen; ACL 2025 (Finding) [PDF] [Code]
Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy
Zhenyuan Guo, Yi Shi, Wenlong Meng, Chen Gong, Chengkun Wei, Wenzhi Chen; ACL 2025 (Finding) [PDF] [Code]
LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors
Chengkun Wei\(^*\), Wenlong Meng\(^*\), Zhikun Zhang, Min Chen, Minghu Zhao, Wenjing Fang, Lei Wang, Zihui Zhang, Wenzhi Chen; NDSS 2024, Distinguished Paper Award (4/140) [PDF] [Code]
DPMLBench: Holistic Evaluation of Differentially Private Machine Learning
Chengkun Wei\(^*\), Minghu Zhao\(^*\), Zhikun Zhang, Min Chen, Wenling Meng, Bo Liu, Yuan Fan, Wenzhi Chen; ACM CCS 2023 [PDF] [Code]
Awards
- NeurIPS 2024 LLM Privacy Challenge, Red-Team First Place
- NDSS 2024 Distinguished Paper
Volunteer
- IEEE T-IFS 2024 Reviewer
Last updated: Jan 18, 2026