Ph.D. Preliminary Oral Exam: Olukorede Fakorede

Olukorede Fakorede
Tuesday, May 30, 2023 - 10:00am
Event Type: 

Techniques for Improving Adversarial Robustness

Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most variants of AT algorithms treat every training example equally. However, recent works have shown that better performance is achievable by treating them unequally. In addition, it has been observed that AT exerts an uneven influence on different classes in a training set and unfairly hurts examples corresponding to classes that are inherently harder to classify. Consequently, various reweighting schemes have been proposed that assign unequal weights to robust losses of individual examples in a training set. In this work, we propose a novel instance-wise reweighting scheme. It considers the vulnerability of each natural example and the resulting information loss on its adversarial counterpart occasioned by adversarial attacks. Through extensive experiments, we show that our proposed method significantly improves over existing reweighting schemes, especially against strong white and black-box attacks.

Adversarial training (AT) methods have been found to be effective against adversarial attacks on deep neural networks. Many variants of AT have been proposed to improve its performance. Pang et al.  have recently shown that incorporating hypersphere embedding (HE) into the existing AT procedures enhances robustness. We observe that the existing AT procedures are not designed for the HE framework, and thus fail to adequately learn the angular discriminative information available in the HE framework. In this work, we propose integrating HE into AT with regularization terms that exploit the rich angular information available in the HE framework. Specifically, our method, termed angular-AT, adds regularization terms to AT that explicitly enforce weight-feature compactness and inter-class separation; all expressed in terms of angular features. Experimental results show that angular-AT further improves adversarial robustness.

Committee: Jin Tian (major professor), Ali Jannesari, Qi Li, Chris Quinn, and Robyn Lutz

Join on Zoom: