About me

Yuhang Wu (邬雨航) is currently a first-year graduate student in Electronic Information at Shanghai University of Engineering Science.

📧 You can contact me via vovyh0514@gmail.com (Please state your purpose / 请您注明来意)

🚀 Current Status / 目前状态 First-year graduate student in Electronic Information, focusing on cutting-edge research in AI security and related fields.

🧠 Research Interests / 研究兴趣

1. Security of Large Language Models (LLM) / 大语言模型（LLM）安全
2. Interpretability of AI Systems / 人工智能系统的可解释性
3. Trustworthy & Reliable AI / 可信与可靠人工智能

⚡ Key Achievements / 主要成果

• Top Ten Projects & Outstanding Project Award, Shusheng Training Camp, Shanghai Artificial Intelligence Laboratory / 上海人工智能实验室书生训练营 十佳项目 & 优秀项目
• [EMNLP2025] Sugar-Coated Poison: Benign Generation Unlocks Jailbreaking

🤝 Collaboration / 合作意向 Open to collaboration on projects related to AI security, LLM interpretability, and trustworthy AI. Feel free to reach out with potential cooperation opportunities!

Publications

Details in Publications Page

Total Publications: 0

• ⭐: Co-first Author
• 🚩: Corresponding Author
• 💭: Under Review