paper-with-me

홈 › Papers

Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs

2025-06-15 · Lu Chen, Han Yang, Hu Wang, Yuxin Cao, Shaofeng Li, Yuan Luo

Adversarial examples have attracted significant attention over the years, yet understanding their frequency-based characteristics remains insufficient. In this paper, we investigate the intriguing properties of adversarial examples in the frequency domain for the image classification task, with the following key findings. (1) As the high-frequency components increase, the performance gap between adversarial and natural examples becomes increasingly pronounced. (2) The model performance against filtered adversarial examples initially increases to a peak and declines to its inherent robustness. (3) In Convolutional Neural Networks, mid- and high-frequency components of adversarial examples exhibit their attack capabilities, while in Transformers, low- and mid-frequency components of adversarial examples are particularly effective. These results suggest that different network architectures have different frequency preferences and that differences in frequency components between adversarial and natural examples may directly influence model robustness. Based on our findings, we further conclude with three useful proposals that serve as a valuable reference to the AI model security community.

📄 PDF Abstract BibTeX arXiv:2506.12875

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustnessimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain

2022-11-01 · NIPS 2022 11 · Yiting Chen, Qibing Ren, Junchi Yan

The existence of adversarial examples poses concerns for the robustness of convolutional neural networks (CNN), for which a popular hypothesis is about the frequency bias phenomenon: CNNs rely more on high-frequency comp…

Adversarial AttackAdversarial RobustnessData AugmentationFairness+2

Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs

2021-10-06 · Philipp Benz, Soomin Ham, Chaoning Zhang, Adil Karjauv 외

Convolutional Neural Networks (CNNs) have become the de facto gold standard in computer vision applications in the past years. Recently, however, new model architectures have been proposed challenging the status quo. The…

Adversarial AttackAdversarial Robustness

Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?

2022-03-16 · ICLR 2022 4 · Yonggan Fu, Shunyao Zhang, Shang Wu, Cheng Wan 외

Vision transformers (ViTs) have recently set off a new wave in neural architecture design thanks to their record-breaking performance in various vision tasks. In parallel, to fulfill the goal of deploying ViTs into real-…

Exploring Frequency Domain Interpretation of Convolutional Neural Networks

2019-11-27 · Zhongfan Jia, Chenglong Bao, Kaisheng Ma

Many existing interpretation methods of convolutional neural networks (CNNs) mainly analyze in spatial domain, yet model interpretability in frequency domain has been rarely studied. To the best of our knowledge, there i…

Evaluating Adversarial Robustness in the Spatial Frequency Domain

2024-05-10 · Keng-Hsin Liao, Chin-Yuan Yeh, Hsi-Wen Chen, Ming-Syan Chen

Convolutional Neural Networks (CNNs) have dominated the majority of computer vision tasks. However, CNNs' vulnerability to adversarial attacks has raised concerns about deploying these models to safety-critical applicati…

Adversarial Robustness