The robustness in Learning theory
Organizer
Speaker
Time
Monday, May 29, 2023 4:00 PM - 4:30 PM
Venue
数学系理科楼A-203
Abstract
In this report, I shall introduce the theory robustness of neural networks. Extensive studies have been devoted to developing neural networks with certified robustness guarantees. Existing approaches can be mainly divided into the following three categories: certified defenses via randomized smoothing, certified defenses for standard networks and certified defenses using Lipschitz networks. I will introduce recent work on robustness of neural networks.