Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913895331921920 |
|---|---|
| author | Chen, Lu Yang, Han Wang, Hu Cao, Yuxin Li, Shaofeng Luo, Yuan |
| author_facet | Chen, Lu Yang, Han Wang, Hu Cao, Yuxin Li, Shaofeng Luo, Yuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12875 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs Chen, Lu Yang, Han Wang, Hu Cao, Yuxin Li, Shaofeng Luo, Yuan Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2506.12875 |