Multiple Adversarial Domains Adaptation Approach for Mitigating Adversarial Attacks Effects. (10th October 2022)

• Record Type: Journal Article
• Authors: Rasheed, Bader; Khan, Adil; Ahmad, Muhammad; Mazzara, Manuel; Kazmi, S. M. Ahsan
• Other Names: Sitharthan R. Academic Editor.
• Is Part Of: International transactions on electrical energy systems. Volume 2022(2022)
• Publication Date: 2022-10-10
• Subjects: Electric power -- Periodicals; Electric power systems -- Periodicals; Electrical engineering -- Periodicals; 621.3
• DOI: 10.1155/2022/2890761
• Languages: English
• ISSNs: 2050-7038

Abstract

Abstract : Although neural networks are near achieving performance similar to humans in many tasks, they are susceptible to adversarial attacks in the form of a small, intentionally designed perturbation, which could lead to misclassifications. The best defense against these attacks, so far, is adversarial training (AT), which improves a model's robustness by augmenting the training data with adversarial examples. However, AT usually decreases the model's accuracy on clean samples and could overfit to a specific attack, inhibiting its ability to generalize to new attacks. In this paper, we investigate the usage of domain adaptation to enhance AT's performance. We propose a novel multiple adversarial domain adaptation (MADA) method, which looks at this problem as a domain adaptation task to discover robust features. Specifically, we use adversarial learning to learn features that are domain-invariant between multiple adversarial domains and the clean domain. We evaluated MADA on MNIST and CIFAR-10 datasets with multiple adversarial attacks during training and testing. The results of our experiments show that MADA is superior to AT on adversarial samples by about 4% on average and on clean samples by about 1% on average.