Dr. Yue Zhao is an Assistant Professor of Computer Science at the University of Southern California, where he leads the FORTIS Lab. He serves as Associate Co-Director of the USC Institute on Ethics and Trust in Computing for 2026-2027. He received his Ph.D. from Carnegie Mellon University's Heinz College of Information Systems and Public Policy in 2023. His lab develops theory, methods, benchmarks, and open-source tools for Auditable AI Systems across four directions: detection in data, verification of output, auditing of action, and modeling of risk. The program spans anomaly detection, LLM evaluation, agent security and efficiency, and a developing direction connecting behavioral evidence to deployment risks and potential losses. Its current focus is open-source infrastructure for auditing autonomous agents before deployment and after a run. His lab also studies how LLMs and agents can affect people and the decisions made with them.
Dr. Zhao has authored over 80 peer-reviewed papers. His open-source projects, including PyOD, ADBench, TrustLLM, agent-audit, and Aegis, together exceed 65 million downloads and 30,000 GitHub stars. PyOD is named by OpenAI, used by Apache Beam, Amazon, Walmart, Databricks, and the European Space Agency, and discussed in five books. The anomaly-detection tools are cited in 97 patents. TrustLLM is cited in a U.S. Senate committee report, a NIST special publication on adversarial machine learning, and the 2025 and 2026 editions of the International AI Safety Report.
His honors include the NVIDIA Academic Grant Program Award, multiple Amazon Research Awards, the Capital One Research Award, and the Foresight Institute AI for Safety & Science Nodes Grant. A Meta sponsored research agreement also supports the lab. AAAI selected him for New Faculty Highlights, and his papers have won a Best Short Paper Award at ACM SIGSPATIAL and a Second Prize CCC Award at the IEEE ICDM BlueSky Track. He is an Action Editor for Transactions on Machine Learning Research and the Journal of Data-centric Machine Learning Research, and an Associate Editor for ACM Transactions on AI for Science and IEEE Transactions on Neural Networks and Learning Systems.