Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning

2022/11/04 by Anaelia Ovalle, Ovalle, Anaelia, Evan Czyzycki +4
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.AI #cs.CR #cs.LG

paper · pdf · doi:10.48550/arxiv.2211.02468

v1

arxiv created 2022/11/04 · openalex publication_date 2022/11/04 · arxiv updated 2022/11/07 · openalex created_date 2022/11/12 · openalex updated_date 2026/07/28

Abstract

Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such that its corresponding model output changes. These sensitivity attacks exploit the model's sensitivity toward task-irrelevant features. Another form of adversarial sample can be crafted via invariance attacks, which exploit the model underestimating the importance of relevant features. Previous literature has indicated a tradeoff in defending against both attack types within a strictly L_p bounded defense. To promote robustness toward both types of attacks beyond Euclidean distance metrics, we use metric learning to frame adversarial regularization as an optimal transport problem. Our preliminary results indicate that regularizing over invariant perturbations in our framework improves both invariant and sensitivity defense.

Related

• Metric Learning for Adversarial Robustness
• Enhancing Adversarial Robustness for Deep Metric Learning
• Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples
• Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness
• Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey