Portrait of Pei Chen

Pei Chen

Ph.D. Candidate
Fudan University
System Software and Security Lab
peichen19 [AT] fudan.edu.cn


Research Interests

News

Publications

  1. PRISON: Unmasking the Criminal Potential of Large Language Models
    Xinyi Wu, Geng Hong, Pei Chen, Yueyue Chen, Xudong Pan, Min Yang
    The International Conference on Learning Representations (ICLR), 2026
    PDF
  2. Unveiling the Resilience of LLM-Enhanced Search Engines Against Black-Hat SEO Manipulation
    Pei Chen, Geng Hong, Xinyi Wu, Mengying Wu, Zixuan Zhu, Mingxuan Liu, Baojun Liu, Mi Zhang, Min Yang
    The ACM Web Conference (WWW), 2026
    PDF
  3. When Fun Turns Toxic: A First Look at Aggressive Advertising in Mini-games
    Pei Chen, Geng Hong, Yicheng Qin, Huazhe Wang, Mengying Wu, Min Yang, Ziru Zhao, Yuanpeng Zhu, Tao Su
    The 35th USENIX Security Symposium (USENIX Security), 2026
    PDF
  4. You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense
    Wuyuao Mai, Geng Hong, Pei Chen, Xudong Pan, Baojun Liu, Yuan Zhang, Haixin Duan, Min Yang
    The ACM Web Conference (WWW), 2025
    PDF
  5. Fast Play, Fast Profit: Unveiling the Prevalence of Aggressive Ad Behaviors in Mini-Game
    Pei Chen, Geng Hong, Yicheng Qin, Huazhe Wang, Mengying Wu, Yuan Zhang, Min Yang, Ziru Zhao, Yuanpeng Zhu, Tao Su
    ACM Workshop on Security and Privacy of AI-Empowered Mobile Super Apps (SaTS), 2025
    PDF
  6. Underground Application Collection Method Based on Spiking Traffic Analysis (一种基于突变流量的在野黑产应用采集方法)
    Pei Chen, Geng Hong, Mengying Wu, Jinsong Chen, Haixin Duan, Min Yang
    Journal of Software (软件学报), 2024
    PDF_CN PDF_EN
  7. Understanding and Detecting Abused Image Hosting Modules as Malicious Services
    Geng Hong, Mengying Wu, Pei Chen, Xiaojing Liao, Guoyi Ye, Min Yang
    ACM SIGSAC Conference on Computer and Communications Security (CCS), 2023
    PDF

Preprints

  1. FlowGuard: From Signals to Evidence for MCP Security Detection
    Baichao An, Pei Chen, Geng Hong, Yueyue Chen, Mengying Wu
    arXiv preprint, 2026
    PDF
  2. Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers and Security Scanner Reliability
    Pei Chen, Baichao An, Mengying Wu, Binwang Wan, Geng Hong, Jinsong Chen, Xudong Pan, Jiarun Dai, Min Yang
    arXiv preprint, 2026
    PDF
  3. MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent
    Mengying Wu, Pei Chen, Geng Hong, Baichao An, Jinsong Chen, Binwang Wan, Xudong Pan, Jiarun Dai, Min Yang
    arXiv preprint, 2025
    PDF

Projects

MCPZoo project homepage showing its runnable MCP server repository

MCPZoo

A continuously growing repository that collects MCP servers from diverse sources and turns them into unified, runnable samples for ecosystem measurement and security research.

Website Paper
AgentGuard protection across the AI agent lifecycle

AgentGuard

A zero-trust security foundation that integrates with existing agent frameworks and applies configurable safeguards across LLM calls and tool execution, with runtime monitoring and post-hoc auditing.

Website Code

Services

Program Committees