publications

Some interesting works...

2026

  1. USENIX
    cordyceps.png
    Cordyceps: Covert Control Attacks on LLMs via Data Poisoning
    Zedian Shao, Charles Fleming, and Teodora Baluta
    In USENIX Security Symposium, 2026
    arXiv
  2. ACL
    imageprotector.png
    Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
    Zedian Shao*, Hongbin Liu*, Yuepeng Hu, and Neil Zhenqiang Gong
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2026
    arXiv
  3. SACMAT
    A Critical Evaluation of Defenses against Prompt Injection Attacks
    Yuqi Jia, Zedian Shao, Yupei Liu, Jinyuan Jia, Dawn Song, and Neil Zhenqiang Gong
    In ACM Symposium on Access Control Models and Technologies (ACM SACMAT), 2026
    arXiv

2025

  1. AISec
    poisonedalign.png
    Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
    Zedian Shao*, Hongbin Liu*, Jaden Mu, and Neil Zhenqiang Gong
    In ACM Workshop on Artificial Intelligence and Security (AISec), 2025
    DOI arXiv
  2. EMNLP
    WebInject: Prompt Injection Attack to Web Agents
    Xilong Wang, John Bloch, Zedian Shao, Yuepeng Hu, Shuyan Zhou, and Neil Zhenqiang Gong
    In Empirical Methods in Natural Language Processing (EMNLP), 2025
    arXiv
  3. S&P
    promptlocate.png
    PromptLocate: Localizing Prompt Injection Attacks
    Yuqi Jia, Yupei Liu, Zedian Shao, Jinyuan Jia, and Neil Zhenqiang Gong
    In IEEE Symposium on Security and Privacy (S&P), 2025
    arXiv

2024

  1. The Evolution of Detection Systems and their Application for Intelligent Transportation Systems: From Solo to Symphony
    Zedian Shao, Kun Yang, Peng Sun, Yulin Hu, and Azzedine Boukerche
    Computer Communications, 2024
  2. ECCV
    Align Before Collaborate: Mitigating Feature Misalignment for Robust Multi-Agent Perception
    Kun Yang, Dingkang Yang, Ke Li, Dongling Xiao, Zedian Shao, Peng Sun, and Liang Song
    In European Conference on Computer Vision (ECCV), 2024
    Oral Presentation
  3. Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models
    Zhongye Liu*, Hongbin Liu*, Yuepeng Hu, Zedian Shao, and Neil Zhenqiang Gong
    arXiv, 2024
    arXiv
  4. Refusing Safe Prompts for Multi-modal Large Language Models
    Zedian Shao*, Hongbin Liu*, Yuepeng Hu, and Neil Zhenqiang Gong
    arXiv, 2024
    arXiv

2023

  1. Modern Deep Learning-Based Object Detection Methods for Supporting Intelligent Transportation Systems: A Comparative Study
    Zedian Shao, Peng Sun, Yulin Hu, and Azzedine Boukerche
    In 2023 3rd International Conference on Networking Systems of AI (INSAI), 2023