Bo Li: Trustworthy Machine Learning: Robustness, Privacy, Generalization, and their Interconnections

Описание: Advances in machine learning have led to the rapid and widespread deployment of learning-based methods in safety-critical applications, such as autonomous driving and medical healthcare. Standard machine learning systems, however, assume that training and test data follow the same or similar distributions, without explicitly considering active adversaries manipulating either distribution. For instance, recent work demonstrates that motivated adversaries can circumvent anomaly detection or other machine learning models at test-time through evasion attacks, or can inject well-crafted malicious instances into training data to induce errors during inference through poisoning attacks. Such distribution shifts could also lead to other trustworthiness issues, such as generalization. In this talk, we describe different perspectives of trustworthy machine learning, such as robustness, privacy, generalization, and their underlying interconnections. We focus on a certifiably robust learning approach based on statistical learning with logical reasoning as an example, and then discuss the principles towards designing and developing practical trustworthy machine learning systems with guarantees, by considering these trustworthiness perspectives holistically.