"Pete leads Microsoft's AI Red Team, working to identify key security and safety risks in the AI systems Microsoft develops and uses.
The team research, develop, and deploy novel attacks against AI systems and work with product teams to develop controls and mitigations for the new and emerging attack techniques.
Prior to this Pete was a security researcher in the Microsoft Threat Intelligence Center (MSTIC) where he led a team developing detections to detect key threat actors, and their techniques in Microsoft's Defender and Sentinel products. He is also the co-author and maintainer of the MSTICPy package - an open sourcelibrary for security investigation and hunting in Jupyter Notebooks.