As organizations adopt AI technologies they inherit AI failures. These failures often manifest themselves in AI models that produce erroneous predictions that go undetected. In Stanford MLSys Seminar 2021, Robust Intelligence Co-founder & CEO Yaron Singer discusses root causes for AI models going haywire, and present a rigorous framework for eliminating risk from AI. He shows how this methodology can be used as building blocks for continuous testing and firewall systems for AI.
June 21, 2021
How To Secure AI Systems @ Stanford MLSys Seminar