鉴别器
对抗制
稳健性(进化)
计算机科学
人工智能
深层神经网络
模式识别(心理学)
机器学习
数据挖掘
深度学习
生物化学
基因
电信
化学
探测器
作者
Hong Wang,Yuefan Deng,Shinjae Yoo,Yuewei Lin
出处
期刊:IEEE transactions on cybernetics
[Institute of Electrical and Electronics Engineers]
日期:2024-01-01
卷期号:: 1-11
标识
DOI:10.1109/tcyb.2024.3380437
摘要
While deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this article, we strive to explore the robust features that are not affected by the adversarial perturbations, that is, invariant to the clean image and its adversarial examples (AEs), to improve the model's adversarial robustness. Specifically, we propose a feature disentanglement model to segregate the robust features from nonrobust features and domain-specific features. The extensive experiments on five widely used datasets with different attacks demonstrate that robust features obtained from our model improve the model's adversarial robustness compared to the state-of-the-art approaches. Moreover, the trained domain discriminator is able to identify the domain-specific features from the clean images and AEs almost perfectly. This enables AE detection without incurring additional computational costs. With that, we can also specify different classifiers for clean images and AEs, thereby avoiding any drop in clean image accuracy.
科研通智能强力驱动
Strongly Powered by AbleSci AI