VAHLIS, YEVGENIY

Topic : DIFFERENTIAL PRIVACY IN THE REAL WORLD

Abstract:  (1) Yes, so through well crafted adversarial inputs machine learning models can be subverted by an attacker. Combine these facts with a model that aggregates data from a multitude of customers and you have an AI-driven disaster waiting to happen. In this talk we will cover a defensive signature called “differential privacy” that is a potential solution to other threats.In this talk Yevgeniy will explain the core concepts of differential privacy and share a behind the scenes look at how three leading SaaS companies are have performed performing separate privacy in their products

Bio:  Yevgeniy Vahlis is the Director of Applied Research at Georgian Partners, a Toronto-based growth equity firm those invests in SaaS-based business software companies. Prior to joining Georgian Partners, he was a Senior Engineer at Amazon, where worked on deep learning Applied to demand forecasting. Previous to that, Yevgeniy worked at Nymi, a biometrics security startup, and at AT & T’s Security Research Center. He holds a Ph.D. in theoretical computer science from the University of Toronto.