Fighting fire with fire: A spatial–frequency ensemble relation network with generative adversarial learning for adversarial image classification. Issue 5 (26th January 2021)

• Record Type: Journal Article
• Authors: Zheng, Wenbo; Yan, Lan; Gou, Chao; Wang, Fei‐Yue
• Is Part Of: International journal of intelligent systems. Volume 36:Issue 5(2021)
• Page Start: 2081
• Page End: 2121
• Publication Date: 2021-01-26
• Subjects: adversarial examples -- ensemble learning -- generative adversarial learning -- image classification -- meta‐learning; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; 006.3
• DOI: 10.1002/int.22372
• Languages: English
• ISSNs: 0884-8173

Abstract

Abstract: Adversarial images generated by generative adversarial networks are not close to any existing benign images, and contain nonrobust features that have been identified as critical to the robustness of a machine learning model. Since adversarial images have an underlying distribution that differs from normal images, these kinds of images can offer valuable features for training a robust model. To deal with these special features, we focus on a novel machine learning task of adversarial images classification, where adversarial images can be used to investigate the problem of classifying adversarial images themselves. In the setting of this novel task, adversarial images are the ONLY kind of data used in training and testing, rather than not just a set of testing images as usual. To this end, we propose a novel spatial–frequency ensemble relation network with generative adversarial learning. First, we present a spatial–frequency ensemble representation learning to extract the feature of training images. Second, we design a meta‐learning‐based relation model to gain the relationship between images. Third, to achieve a robust model, we utilize generative adversarial learning and transform the relationship into a Jacobian matrix. Finally, we design a discriminator model that determines whether an adversarial image is from the matching category or not. Experimental results demonstrate that our approach achieves significantly higher performance compared with other state‐of‐the‐arts.