Research

AI-driven security and software engineering

Modern society depends on critical infrastructure run by large, complex software, but software is expensive to develop and difficult to verify. AI is changing how we build, verify, and maintain software. Towards this goal, we are making progress on:

• LLM-driven specification discovery and bug detection (S&P 2026, Usenix Security 2026)
• LLM-driven fuzzing (ACL 2026, AST 2026, EMNLP 2025, ICSE 2025, CCS 2024, CCS 2023)
• Evaluate LLM on program understanding (NeurIPS 2025)

Trustworthy AI

While machine learning has made great strides, it isn't ready for many scenarios because of concerns over its security, privacy, and robustness. We are making progress towards trustworthy AI, including:

• AI agent security (RAIE)
• Attack against safety-aligned LLMs (NeurIPS 2024)