Victoria Westerhoff

Tori Westerhoff is a Principal AI Security Researcher and Director of Microsoft's AI Red Team Operations. She manages the team of AI hackers who test high risk GenAI across models, systems, and products. Tori leads red teaming strategy for AI Security, Responsible AI, and Frontier Harms, driving innovation on AI red teaming methods for novel AI harms. Tori brings 15+ years of strategy, technology, and analytics experience across Microsoft and national security organizations, via Deloitte Consulting, such as the CIA, FBI, Department of State, and Homeland Security. Her broad approach to AI security pulls from her degree in Cognitive Neuroscience at Yale with Honors and her MBA from Wharton at UPenn, where she served as a Leadership Fellow and researched with Wharton Neuroscience Initiative.