Hi there, I'm Yue Zhao (赵越) 👋
😄 I am an Assistant Professor at USC Computer Science and a faculty member of the USC Machine Learning Center. I lead the FORTIS Lab (Foundations for Observable, Robust, and Trustworthy Intelligent Systems). More information can be found on my homepage.
External Affiliation Disclosure:
As of 02/01/2026, Dr. Zhao does not currently hold any industry employment, consulting, or advisory appointments.
My research focuses on auditing, securing, and deploying reliable AI systems, with an emphasis on foundation models and agentic systems operating in real-world environments.
I study how foundation models, tool-using agents, and multi-agent systems can produce traceable evidence of their behavior, support meaningful audit after deployment, satisfy checkable safety and policy requirements, and operate reliably in high-stakes settings.
- Email: yue.z [AT] usc.edu
- 🌐 Homepage
- 📚 Google Scholar
- 🧠 GitHub
💡 I am the creator/core developer of several widely used ML systems including PyOD, PyGOD, ADBench, Aegis, and TrustLLM, which together have 35M+ downloads and 22K+ GitHub stars. These tools are used across academia, industry, and government, including by NASA, Tesla, Morgan Stanley, and the U.S. Senate.