Salient Feature Extractor for Adversarial Defense on Deep Neural Networks
This addresses the security problem of adversarial attacks on deep learning models in computer vision, offering an incremental improvement with interpretable defense mechanisms.
The paper tackles the vulnerability of deep neural networks to adversarial attacks by proposing a salient feature extractor (SFE) that separates class-related and misleading features for detection and defense, achieving state-of-the-art results on MNIST, CIFAR-10, and ImageNet datasets.
Recent years have witnessed unprecedented success achieved by deep learning models in the field of computer vision. However, their vulnerability towards carefully crafted adversarial examples has also attracted the increasing attention of researchers. Motivated by the observation that adversarial examples are due to the non-robust feature learned from the original dataset by models, we propose the concepts of salient feature(SF) and trivial feature(TF). The former represents the class-related feature, while the latter is usually adopted to mislead the model. We extract these two features with coupled generative adversarial network model and put forward a novel detection and defense method named salient feature extractor (SFE) to defend against adversarial attacks. Concretely, detection is realized by separating and comparing the difference between SF and TF of the input. At the same time, correct labels are obtained by re-identifying SF to reach the purpose of defense. Extensive experiments are carried out on MNIST, CIFAR-10, and ImageNet datasets where SFE shows state-of-the-art results in effectiveness and efficiency compared with baselines. Furthermore, we provide an interpretable understanding of the defense and detection process.