Dataisland / security research

Zheng Yu 于ε³₯

I build agents and systems for finding, understanding, and repairing vulnerabilities.

Now

Security Researcher at DepthFirst, working on LLM-based agents for vulnerability discovery, repair, and penetration testing.

PhD in Computer Science from Northwestern University; bachelor's degree from the ACM Honor Class at Shanghai Jiao Tong University.

News

  • pPatch accepted to ACM FSE 2026.

  • Joined DepthFirst as a Security Research Engineer.

  • Passed PhD defense at Northwestern.

  • I got πŸ₯ˆ Runner-up in Technical Impact Award of CSAW Applied Research Competition (ARC) 2025!

  • PC member for LLM4Code 2026 at ICSE.

  • Passed PhD proposal exam.

  • PatchAgent selected as a CSAW ARC 2025 finalist.

  • PortGPT accepted to IEEE S&P 2026.

  • Our team, 42-b3yond-6ug, won rank 6 at AIxCC Finals!

  • Awarded Student Grant from USENIX Security 2025!

  • PatchAgent accepted to USENIX Security 2025.

  • Received MS in Computer Science from Northwestern.

  • Passed PhD qualifying exam.

  • Awarded Student Grant from ACM CCS 2024!

  • Our team, 42-b3yond-6ug, won the AIxCC Semi-Finals and was awarded $2 million. I had the honor of designing the program repair system for the competition.

  • Awarded Student Grant from USENIX Security 2024!

  • LLM-Fuzzer accepted to USENIX Security 2024.

  • ShadowBound accepted to USENIX Security 2024.

  • Our team, 42-b3yond-6ug, received funding of $1 million from AIxCC.

  • CAMP accepted to USENIX Security 2024.

Experience

  • DepthFirst / Security Researcher AI Security Team

  • CertiK / Security Researcher Smart Contract Security Team

  • University of Waterloo / Visiting Researcher CrySP Lab, Advisor: Prof. Meng Xu

  • Google Summer of Code / GSOC Project Mentor Bridging Qiling and Static Analysis

  • JD.COM, Inc. / Security Engineer Application Security Team - Firmware Emulation

  • Shanghai Jiao Tong University / Infrastructure Engineer Information and Network Center

Writing All notes β†’
  • Inside the V8 Sandbox

    Notes on V8's sandbox threat model, attack boundary, and the browser code that still has to treat sandbox data carefully.

  • Learning Lean as a Programmer

    Learning Lean from the perspective of a programmer: types as propositions, proofs as programs, and raw induction machinery.

  • Bitcoin From the Top Down

    A top-down walkthrough of Bitcoin's data model, from peer-to-peer state to transactions, UTXOs, and script validation.

Selected Research All papers β†’
  1. pPatch: Automated Vulnerability Unpatching ACM International Conference on the Foundations of Software Engineering (FSE) 2026
  2. PortGPT: Towards Automated Backporting Using Large Language Models IEEE Symposium on Security and Privacy (S&P) 2026
  3. PatchAgent: A Practical Program Repair Agent Mimicking Human Expertise USENIX Security Symposium 2025 (Long Presentation)
  4. ShadowBound: Efficient Heap Memory Protection Through Advanced Metadata Management and Customized Compiler Optimization USENIX Security Symposium 2024
  5. LLM-Fuzzer: Scaling Assessment of Large Language Model Jailbreaks USENIX Security Symposium 2024
  6. Reversing MCU with Firmware Emulation BlackHat Europe 2022, London, UK