Robust Representation Consistency Model via Contrastive Denoising
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_ | 1866909667662233600 |
|---|---|
| author | Lei, Jiachen Berner, Julius Wang, Jiongxiao Chen, Zhongzhu Ba, Zhongjia Ren, Kui Zhu, Jun Anandkumar, Anima |
| author_facet | Lei, Jiachen Berner, Julius Wang, Jiongxiao Chen, Zhongzhu Ba, Zhongjia Ren, Kui Zhu, Jun Anandkumar, Anima |
| contents | Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently, diffusion models have been successfully employed for randomized smoothing to purify noise-perturbed samples before making predictions with a standard classifier. While these methods excel at small perturbation radii, they struggle with larger perturbations and incur a significant computational overhead during inference compared to classical methods. To address this, we reformulate the generative modeling task along the diffusion trajectories in pixel space as a discriminative task in the latent space. Specifically, we use instance discrimination to achieve consistent representations along the trajectories by aligning temporally adjacent points. After fine-tuning based on the learned representations, our model enables implicit denoising-then-classification via a single prediction, substantially reducing inference costs. We conduct extensive experiments on various datasets and achieve state-of-the-art performance with minimal computation budget during inference. For example, our method outperforms the certified accuracy of diffusion-based methods on ImageNet across all perturbation radii by 5.3% on average, with up to 11.6% at larger radii, while reducing inference costs by 85$\times$ on average. Codes are available at: https://github.com/jiachenlei/rRCM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13094 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Representation Consistency Model via Contrastive Denoising Lei, Jiachen Berner, Julius Wang, Jiongxiao Chen, Zhongzhu Ba, Zhongjia Ren, Kui Zhu, Jun Anandkumar, Anima Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently, diffusion models have been successfully employed for randomized smoothing to purify noise-perturbed samples before making predictions with a standard classifier. While these methods excel at small perturbation radii, they struggle with larger perturbations and incur a significant computational overhead during inference compared to classical methods. To address this, we reformulate the generative modeling task along the diffusion trajectories in pixel space as a discriminative task in the latent space. Specifically, we use instance discrimination to achieve consistent representations along the trajectories by aligning temporally adjacent points. After fine-tuning based on the learned representations, our model enables implicit denoising-then-classification via a single prediction, substantially reducing inference costs. We conduct extensive experiments on various datasets and achieve state-of-the-art performance with minimal computation budget during inference. For example, our method outperforms the certified accuracy of diffusion-based methods on ImageNet across all perturbation radii by 5.3% on average, with up to 11.6% at larger radii, while reducing inference costs by 85$\times$ on average. Codes are available at: https://github.com/jiachenlei/rRCM. |
| title | Robust Representation Consistency Model via Contrastive Denoising |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.13094 |