# Salient Feature Extractor for Adversarial Defense on Deep Neural Networks

Source: [Salient Feature Extractor for Adversarial Defense on Deep Neural Networks](<https://www.sota2.com/research/paper/68fa69f31e209131cea25305>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:12:37.633Z

Authors: Jinyin Chen, Ruoxi Chen, Haibin Zheng, Zhaoyan Ming, Wenrong Jiang, Chen Cui

Published: 2021-05-14T12:56:06.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2105.06807>)

[PDF](<https://arxiv.org/pdf/2105.06807.pdf>)
