Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913465610797056 |
|---|---|
| author | Zhang, Mingkun Li, Jianing Chen, Wei Guo, Jiafeng Cheng, Xueqi |
| author_facet | Zhang, Mingkun Li, Jianing Chen, Wei Guo, Jiafeng Cheng, Xueqi |
| contents | Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05900 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information Zhang, Mingkun Li, Jianing Chen, Wei Guo, Jiafeng Cheng, Xueqi Computer Vision and Pattern Recognition Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods. |
| title | Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.05900 |