See my Google Scholar, DBLP, ORCID, and ResearchGate for the full publication list. Use Yue Zhao BibTeX (single file) for copy/paste. †Equal contribution and ♠Corresponding author for multi-first/corresponding author papers.
This list emphasizes work on AI risk audit and control across the deployment stack: anomaly and out-of-distribution detection in data, trust and robustness evaluation of foundation models, and runtime audit and control of deployed agent systems.