I am an Assistant Professor of Computer Science at William & Mary and a member of the W&M Cybersecurity Center. Before joining W&M, I was a Research Scientist at the IBM Thomas J. Watson Research Center. I received my Ph.D. in Computer Science from Indiana University Bloomington in 2024, advised by Xiaojing Liao and Luyi Xing.
My research lies at the intersection of security and large language models. I study how LLMs and AI agents can be used to find and assess vulnerabilities at scale, how to secure agentic AI systems themselves, and how to protect software supply chains and user privacy in mobile ecosystems. My work combines program analysis, machine learning, and large-scale measurement, and appears at venues such as USENIX Security, ACM CCS, NDSS, ICML, and KDD. Our findings have led to security fixes and bug bounties from Facebook, Google, Twitter, Tencent, and Opera.
Prospective students: I am looking for self-motivated Ph.D. students and research interns. Please fill out this interest form and apply through the W&M graduate portal.
Selected Publications (full list)
-
USENIX Sec
From Assistance to Autonomy: An Empirical Study of AI Use in a Live Capture-the-Flag (CTF) Competition
USENIX Security Symposium, 2026
PDF Artifact Website -
ICML
One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discovery
International Conference on Machine Learning (ICML), 2026
PDF Code -
KDD
OmniVul: A Holistic, Multi-Turn Conversational Benchmark for LLM-Based Vulnerability Assessment
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026
Code -
NDSS
JBomAudit: Assessing the Landscape, Compliance, and Security Implications of Java SBOMs
Network and Distributed System Security Symposium (NDSS), 2025
PDF Code
Distinguished Artifact Award -
CCS
Measuring Compliance Implications of Third-party Libraries’ Privacy Label Disclosure Guidelines
ACM Conference on Computer and Communications Security (CCS), 2024
PDF Project -
USENIX Sec
Lalaine: Measuring and Characterizing Non-Compliance of Apple Privacy Labels at Scale
USENIX Security Symposium, 2023
PDF Code Artifact Appendix Project