Suyoung Lee

I am a postdoctoral researcher at KAIST WSP Lab, advised by Prof. Sooel Son.

My primary research goal is to identify emerging attack surfaces across the Web and AI ecosystems and to develop principled, deployable defenses. My research spans multiple layers of these ecosystems, from AI models to AI-integrated systems.

I’m always happy to hear from you. For all inquiries, you can reach me at suyoung.lee@kaist.ac.kr.

Research Interests
AI Security Web Security Browser Security

Recent News

Jul 2026 I gave an invited talk at the KIISC AI Security Workshop 2026!
Apr 2026 “Overloading Ad Blockers” is accepted to ACM CCS 2026!
Mar 2026 “Site Isolation is Dead” is accepted to IEEE S&P 2026!

Selected Publications

(*: equal contribution)

2026

  1. CCS
    Overloading Ad Blockers: Exploiting Filtering Logic for Selective Denial of Service (To appear)
    Hyunjoon Lee*, Suyoung Lee*, Heiko Kiesel, and Sooel Son
    In Proceedings of the ACM Conference on Computer and Communications Security, 2026
  2. S&P
    Site Isolation is Dead: How Site Isolation is Broken in Agentic Browsers and Extensions
    Suyoung Lee, Seongho Keum, Changoo Lee, Dongwon Shin, Sanghyun Hong, Byoungyoung Lee, and Sooel Son
    In Proceedings of the IEEE Symposium on Security and Privacy, 2026

2023

  1. WWW
    RICC: Robust Collective Classification of Sybil Accounts
    Dongwon Shin*, Suyoung Lee*, and Sooel Son
    In Proceedings of the ACM Web Conference, 2023

2020

  1. SEC
    Montage: A Neural Network Language Model-Guided JavaScript Engine Fuzzer
    Suyoung Lee, HyungSeok Han, Sang Kil Cha, and Sooel Son
    In Proceedings of the USENIX Security Symposium, 2020

Selected Talks

2026

  1. UNIST
    When New Browser Features Become New Attack Surfaces
    Presenter: Suyoung Lee
    UNIST CSE590 Graduate Seminar, Sep 2026
  2. KIISC
    New Security Threats in Agentic Browsers and Extensions
    Presenter: Suyoung Lee
    KIISC AI Security Workshop 2026, Jul 2026