Computer Science Seminar Series: Tianlong Chen

Description

The Computer Science Department presents a hybrid seminar talk featuring Tianlong Chen, a fourth-year Ph.D. candidate of electrical and computer engineering at the University of Texas at Austin. Tianlong Chen will present a seminar titled "How Does an Appropriate Sparsity Benefit Robustness?"

Abstract:

Deep neural networks, or DNNs, are notoriously vulnerable to maliciously crafted adversarial attacks. We conquer this fragility from the network topology perspective. Specifically, we enforce appropriate sparsity forms to serve as an implicit regularization in robust training. In this talk, I will first discuss how sparsity fixes robust overfitting and leads to superior robust generalization. Then, I will present the beneficial role sparsity played in certified robustness. Finally, I will show sparsity can also function as an effective detector to undercover the viciously injected Trojan patterns.

All in-person events at Johns Hopkins must follow university COVID-19 policies. See current guidelines online. This is a hybrid event; please attend the event online by using the Zoom link (email mwade12@jhu.edu for passcode).