Haoyu (Jeffrey) Zhai
I’m currently an MSCS student at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Gang Wang in the Siebel School of Computing and Data Science. My research interests include applying AI into security and privacy-related tasks. My past reserach projects involved using diffusion models, Large Language Models, and AI Agent on real-world security scenarios such as identity de-anonymization and phishing SMS detection. I’m also interested in building explainable and reliable LLMs/Agents for cybersafety (e.g., safe code generation).
My Curriculum Vitae can be found here
News
- 09/2025: Our work Revelio is accepted at IEEE S&P 2026! See you in San Francisco!
- 09/2025: PurpCode is accepted at NeurIPS 2025!
- 07/2025: Our work PurpCode won the 2025 Amazon Nova AI Challenge ($250k prize)!
- 05/2025: Our paper SmishX is accepted at SOUPS 2025!
Publications
IEEE S&P | Revelio: Blurred Images Can Still Disclose Your Identity
Haoyu Zhai*, Shuo Wang*, Qingying Hao, Pirouz Naghavi, Gang Wang
47th IEEE Symposium on Security and Privacy, 2026NeurIPS | PurpCode: Reasoning for Safer Code Generation
Jiawei Liu*, Nirav Diwan*, Zhe Wang*, Haoyu Zhai, Xiaona Zhou, Kiet A. Nguyen, Tianjiao Yu, Muntasir Wahed, Yinlin Deng, Hadjer Benkraouda, Yuxiang Wei, Lingming Zhang, Ismini Lourentzou, Gang Wang
The 39th Annual Conference on Neural Information Processing Systems, 2025SOUPS | Can You Walk Me Through It? Explainable SMS Phishing Detection using LLM-based Agents
Yizhu Wang, Haoyu Zhai, Chenkai Wang, Qingying Hao, Nick A. Cohen, Roopa Foulger, Jonathan A. Handler, Gang Wang The 21st Symposium on Usable Privacy and Security, 2025