Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.11576 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929388171296768 |
|---|---|
| author | Zhang, Kejia Weng, Juanjuan Wu, Junwei Yang, Guoqing Li, Shaozi Luo, Zhiming |
| author_facet | Zhang, Kejia Weng, Juanjuan Wu, Junwei Yang, Guoqing Li, Shaozi Luo, Zhiming |
| contents | The vulnerability of Deep Neural Networks to adversarial perturbations presents significant security concerns, as the imperceptible perturbations can contaminate the feature space and lead to incorrect predictions. Recent studies have attempted to calibrate contaminated features by either suppressing or over-activating particular channels. Despite these efforts, we claim that adversarial attacks exhibit varying disruption levels across individual channels. Furthermore, we argue that harmonizing feature maps via graph and employing graph convolution can calibrate contaminated features. To this end, we introduce an innovative plug-and-play module called Feature Map-based Reconstructed Graph Convolution (FMR-GC). FMR-GC harmonizes feature maps in the channel dimension to reconstruct the graph, then employs graph convolution to capture neighborhood information, effectively calibrating contaminated features. Extensive experiments have demonstrated the superior performance and scalability of FMR-GC. Moreover, our model can be combined with advanced adversarial training methods to considerably enhance robustness without compromising the model's clean accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11576 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness Zhang, Kejia Weng, Juanjuan Wu, Junwei Yang, Guoqing Li, Shaozi Luo, Zhiming Computer Vision and Pattern Recognition The vulnerability of Deep Neural Networks to adversarial perturbations presents significant security concerns, as the imperceptible perturbations can contaminate the feature space and lead to incorrect predictions. Recent studies have attempted to calibrate contaminated features by either suppressing or over-activating particular channels. Despite these efforts, we claim that adversarial attacks exhibit varying disruption levels across individual channels. Furthermore, we argue that harmonizing feature maps via graph and employing graph convolution can calibrate contaminated features. To this end, we introduce an innovative plug-and-play module called Feature Map-based Reconstructed Graph Convolution (FMR-GC). FMR-GC harmonizes feature maps in the channel dimension to reconstruct the graph, then employs graph convolution to capture neighborhood information, effectively calibrating contaminated features. Extensive experiments have demonstrated the superior performance and scalability of FMR-GC. Moreover, our model can be combined with advanced adversarial training methods to considerably enhance robustness without compromising the model's clean accuracy. |
| title | Harmonizing Feature Maps: A Graph Convolutional Approach for Enhancing Adversarial Robustness |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.11576 |