Researcher · Urbana, Illinois

Hwiwon Lee

PhD Student in Computer Science at the University of Illinois Urbana-Champaign · advised by Lingming Zhang.

I build and evaluate AI agents for cybersecurity.

Portrait of Hwiwon Lee
Software security · Agentic systems
01 / Map

Research territories

My work connects the capabilities of AI agents with the evidence, tooling, and evaluation discipline required by real-world security practice.

A · Agents

Agentic Security

Building and evaluating autonomous agents for realistic, long-horizon security workflows.

P.01P.02P.03
B · Systems

Software Systems

Connecting models, program analysis, and dynamic execution evidence in reproducible systems.

P.01P.03P.04
C · Practice

Applied Vulnerability Research

Discovering and validating vulnerabilities in production software, from services to operating-system kernels.

P.02P.04
02 / Work

Selected publications

  1. P.01
    arXiv ’26

    SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

    Hwiwon Lee, Jiawei Liu, Dongjun Kim, Wubing Xia, Ziqi Zhang, Chunqiu Steven Xia, Lingming Zhang

    PDF: SEC-bench Pro

  2. P.02
    arXiv ’26

    Agentic Vulnerability Reasoning on COTS Binaries

    Hwiwon Lee, Jongseong Kim, Lingming Zhang

    PDF: Agentic Vulnerability Reasoning on COTS Binaries

  3. P.03
    NeurIPS ’25

    SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks

    Hwiwon Lee, Ziqi Zhang, Hanxiao Lu, Lingming Zhang

    PDF: SEC-bench

  4. P.04
    IEEE S&P ’24

    BENZENE: A Practical Root Cause Analysis System with an Under-Constrained State Mutation

    Younggi Park, Hwiwon Lee, Jinho Jung, Kevin Koo, Huy Kang · Distinguished Paper

    PDF: BENZENE
03 / Now

Recent news

  1. SEC-bench Pro, our benchmark for long-horizon software security tasks, is now available on arXiv.

  2. Agentic Vulnerability Reasoning on COTS Binaries is now available on arXiv.

  3. Recognized as a Microsoft Most Valuable Security Researcher for 2026 Q1.