董英凯，山东大学土建与水利学院工程软件系博士后。研究方向为人工智能应用及安全，当前主要从事人工智能与地球物理学的交叉研究。近两年在国际会议/期刊发表多篇学术论文，其中四大安全顶会两篇。

发表论文：

• Fuzz-testing meets llm-based agents: An automated and efficient framework for jailbreaking text-to-image generation models. Dong, Y., Meng, X., Yu, N., Li, Z., & Guo, S. In 2025 IEEE Symposium on Security and Privacy (SP).

• Safe driving adversarial trajectory can mislead: Toward more stealthy adversarial attack against autonomous driving prediction module. Dong, Y., Wang, L., Li, Z., Li, H., Tang, P., Hu, C., & Guo, S. ACM Transactions on Privacy and Security (TOPS).

• DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation. Gao, X., Meng, X., Dong, Y., Li, Z., & Guo, S. ACM Conference on Computer and Communications Security (CCS).

• Safe-Control: A Safety Patch for Mitigating Unsafe Content in Text-to-Image Generation Models. Meng, X., Dong, Y., Yu, N., Wang, L., Li, Z., & Guo, S. arXiv preprint arXiv:2508.21099.
  

教育背景：

• [1] 2015.09 -- 2019.06

  青岛科技大学       机械工程       工学学士学位

• [2] 2020.09 -- 2025.06

  山东大学       网络与信息安全

• [1] 2025.08 -- 至今

  山东大学