Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM
This addresses the robustness issue in AI security for applications requiring defense against diverse adversarial threats, but it is incremental as it builds on existing FGSM-based techniques.
The paper tackles the problem of deep neural networks' vulnerability to unknown adversarial attacks and the trade-off between clean and adversarial accuracy by proposing a test-time adversarial purification method using FGSM, which improves robust generalization over previous methods.
Numerous studies have demonstrated the susceptibility of deep neural networks (DNNs) to subtle adversarial perturbations, prompting the development of many advanced adversarial defense methods aimed at mitigating adversarial attacks. Current defense strategies usually train DNNs for a specific adversarial attack method and can achieve good robustness in defense against this type of adversarial attack. Nevertheless, when subjected to evaluations involving unfamiliar attack modalities, empirical evidence reveals a pronounced deterioration in the robustness of DNNs. Meanwhile, there is a trade-off between the classification accuracy of clean examples and adversarial examples. Most defense methods often sacrifice the accuracy of clean examples in order to improve the adversarial robustness of DNNs. To alleviate these problems and enhance the overall robust generalization of DNNs, we propose the Test-Time Pixel-Level Adversarial Purification (TPAP) method. This approach is based on the robust overfitting characteristic of DNNs to the fast gradient sign method (FGSM) on training and test datasets. It utilizes FGSM for adversarial purification, to process images for purifying unknown adversarial perturbations from pixels at testing time in a "counter changes with changelessness" manner, thereby enhancing the defense capability of DNNs against various unknown adversarial attacks. Extensive experimental results show that our method can effectively improve both overall robust generalization of DNNs, notably over previous methods.