Title: Robust ML: Progress, challenges, and humans
Abstract: Despite the recent impressive advances in Machine Learning (ML), real-world deployment of ML systems is challenging due to reliability concerns. In this talk, I will discuss the pervasive brittleness of existing ML tools and offer a new perspective on how it arises. I will then describe a conceptual framework that aims to deliver models that are more reliable and robust to adversarial manipulation. Finally, I will outline how this framework differs from the classic ML paradigm, and what benefits it provides, beyond robustness itself.