我们致力于探索大模型时代的系统安全与软件开发前沿，聚焦于底层系统漏洞挖掘（System & IoT Security）、智能代码生成（Coding Agents）以及智能体与具身智能安全（Agent & Embodied AI Security）。我们将大模型能力与领域知识深度融合，面向代码生成与智能体执行中的安全与可靠性问题，构建下一代智能系统的可信基础。
探索利用 Coding Agent 开发真实产品，研发 FastWrite 等智能学术论文写作工具，提升大模型在复杂软件工程场景下的自动化编程与重构能力。
研究自主智能体 (Autonomous Agents) 在交互过程中的安全边界、越权风险以及防御机制，构建 Trustworthy Agents。
Authors: Zhenhao Tian, Yi He, Nuo Zhang, Qixiao Lin, Hetian Shi, Jianwei Zhuge, Jian Mao, Deliang Chang
IEEE Transactions on Information Forensics and Security, 2025
Authors: Yi He, Yunchao Guan, Ruoyu Lun, Shangru Song, Zhihao Guo, Jianwei Zhuge, Jianjun Chen, Qiang Wei, Zehui Wu, Miao Yu, Shi Hetian, Qi Li
Proceedings of USENIX Security Symposium, 2024
Authors: Yuhao Wu, Jinwen Wang, Yujie Wang, Shixuan Zhai, Zihan Li, Yi He, Kun Sun, Qi Li, Ning Zhang
Proceedings of USENIX Security Symposium, 2024
Authors: Xijia Che, Yi He, Xuewei Feng, Kun Sun, Ke Xu, Qi Li
ACM SIGSAC Conference on Computer and Communications Security (CCS), 2024
Authors: Yue Xiao, Yi He, Xiaoli Zhang, Qian Wang, Renjie Xie, Kun Sun, Ke Xu, Qi Li
Network and Distributed System Security (NDSS) Symposium, 2024
Assistant Professor
M.Sc. 2025-2028
M.Sc. 2025-2028
M.Eng. 2025-2027
M.Eng. 2025-2027