Ph.D.


AI Security and Safety Researcher
Artificial Intelligence Institute, CAICT
Beijing, China
CV     GitHub    LinkedIn

Short bio: I am an AI Security and Safety Researcher at the Artificial Intelligence Institute, China Academy of Information and Communications Technology (CAICT), Beijing. I received my Ph.D. in Computer Science and Engineering from the University at Buffalo (SUNY) in 2025, where my advisor was Prof. Hongxin Hu. My doctoral research was supported by the Amazon Research Award. I received my bachelor's degree from Xi'an Jiaotong University.

Research Interests

My research focuses on AI safety benchmarking, Agentic AI security, LLM code security, and cybersecurity evaluation of frontier models. I also contribute to AI safety governance and standardization policy research for the National Development and Reform Commission (NDRC), the Ministry of Industry and Information Technology (MIIT), and the National Data Administration(NDA).

Publications

  1. The Mark Fades: Adaptive Evolutionary Paraphrase-based Attack against LLM Watermarks.

    In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, ACL, 2026

    Yusheng Zhao, Jian Zhao, Tianle Zhang, Feng Wei, and Xuelong Li.

  2. Rethinking Security in LLM Code Generation through Real-World Risk Scenarios.

    In Proceedings of the 23rd Conference on Detection of Intrusions and Malware & Vulnerability Assessment, DIMVA, 2026

    Lixun Ma, Ruolong Ma, Bei Wang, Feng Wei, Zhenguang Liu, Lorenzo Cavallaro, and Wentao Chen.

  3. xNIDS: Explaining Deep Learning-based Network Intrusion Detection Systems for Active Intrusion Responses.

    In Proceedings of the 32nd USENIX Security Symposium, USENIX Security 2023, Anaheim, CA, USA, August 9-11, 2023

    Feng Wei, Hongda Li, Ziming Zhao, and Hongxin Hu.

    [PDF] [Code]

  4. Enabling Dynamic Network Access Control with Anomaly-based IDS and SDN.

    Feng Wei*, Hongda Li*, and Hongxin Hu.

    In Proceedings of ACM International Workshop on Security in Software Defined Networks and Network Function Virtualization (SDN-NFV Security 2019), Richardson, Texas, USA, March 27, 2019. (*co-first author)

    [PDF]

Services

Program Committee Member:


Conference Paper (Sub) Reviewer:


Journal Paper Reviewer:

  • IEEE Transactions on Machine Learning in Communications and Networking
  • IEEE Transactions on Information Forensics and Security
  • IEEE Transactions on Dependable and Secure Computing
  • IEEE Transactions on Cloud Computing
  • IEEE/ACM Transactions on Networking
  • Information Systems Frontiers
  • Computers & Security

Teaching

Competitions and Awards

Hobby

  • I like swimming and sailing.
  • "All men will be sailors then until the sea shall free them." - Leonard Cohen
  • "小舟从此逝，江海寄余生" - 苏轼