MMARD: Improving the Min-Max Optimization Process in Adversarial Robustness Distillation
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_ | 1866915189443526656 |
|---|---|
| author | Wang, Yuzheng Chen, Zhaoyu Yang, Dingkang Wang, Yuanhang Qi, Lizhe |
| author_facet | Wang, Yuzheng Chen, Zhaoyu Yang, Dingkang Wang, Yuanhang Qi, Lizhe |
| contents | Adversarial Robustness Distillation (ARD) is a promising task to boost the robustness of small-capacity models with the guidance of the pre-trained robust teacher. The ARD can be summarized as a min-max optimization process, i.e., synthesizing adversarial examples (inner) & training the student (outer). Although competitive robustness performance, existing ARD methods still have issues. In the inner process, the synthetic training examples are far from the teacher's decision boundary leading to important robust information missing. In the outer process, the student model is decoupled from learning natural and robust scenarios, leading to the robustness saturation, i.e., student performance is highly susceptible to customized teacher selection. To tackle these issues, this paper proposes a general Min-Max optimization Adversarial Robustness Distillation (MMARD) method. For the inner process, we introduce the teacher's robust predictions, which drive the training examples closer to the teacher's decision boundary to explore more robust knowledge. For the outer process, we propose a structured information modeling method based on triangular relationships to measure the mutual information of the model in natural and robust scenarios and enhance the model's ability to understand multi-scenario mapping relationships. Experiments show our MMARD achieves state-of-the-art performance on multiple benchmarks. Besides, MMARD is plug-and-play and convenient to combine with existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06559 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MMARD: Improving the Min-Max Optimization Process in Adversarial Robustness Distillation Wang, Yuzheng Chen, Zhaoyu Yang, Dingkang Wang, Yuanhang Qi, Lizhe Computer Vision and Pattern Recognition Adversarial Robustness Distillation (ARD) is a promising task to boost the robustness of small-capacity models with the guidance of the pre-trained robust teacher. The ARD can be summarized as a min-max optimization process, i.e., synthesizing adversarial examples (inner) & training the student (outer). Although competitive robustness performance, existing ARD methods still have issues. In the inner process, the synthetic training examples are far from the teacher's decision boundary leading to important robust information missing. In the outer process, the student model is decoupled from learning natural and robust scenarios, leading to the robustness saturation, i.e., student performance is highly susceptible to customized teacher selection. To tackle these issues, this paper proposes a general Min-Max optimization Adversarial Robustness Distillation (MMARD) method. For the inner process, we introduce the teacher's robust predictions, which drive the training examples closer to the teacher's decision boundary to explore more robust knowledge. For the outer process, we propose a structured information modeling method based on triangular relationships to measure the mutual information of the model in natural and robust scenarios and enhance the model's ability to understand multi-scenario mapping relationships. Experiments show our MMARD achieves state-of-the-art performance on multiple benchmarks. Besides, MMARD is plug-and-play and convenient to combine with existing methods. |
| title | MMARD: Improving the Min-Max Optimization Process in Adversarial Robustness Distillation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.06559 |