Agentic Security
Designing autonomous agents that can reason across long-horizon, real-world software security workflows.
Software Security · Systems · AI
Hwiwon Lee
PhD Student in Computer Science · UIUC
I build and evaluate AI agents for cybersecurity.
Department of Computer Science, University of Illinois Urbana-Champaign.
Advised by Professor Lingming Zhang.
01 / Focus
Research overview
Software Systems
Building reproducible infrastructure for evaluating, observing, and improving security-oriented systems.
Applied Vulnerability Research
Studying vulnerabilities in production software and translating empirical findings into practical defenses.
02 / Updates
News
-
SEC-bench Pro is now available on arXiv, extending security-agent evaluation to professional workflows.
-
Agentic Vulnerability Reasoning on COTS Binaries is now available on arXiv.
-
Recognized as a Microsoft Most Valuable Security Researcher for 2026 Q1.
03 / Work