Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation
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_ | 1866913508411572224 |
|---|---|
| author | Wu, Tsung-Han Su, Hung-Ting Chen, Shang-Tse Hsu, Winston H. |
| author_facet | Wu, Tsung-Han Su, Hung-Ting Chen, Shang-Tse Hsu, Winston H. |
| contents | The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training. To explore the possibility of tackling more complicated tasks with even lower labeling budgets, unlike prior approaches that rely on robust pretrained models, we present SNORD - a simple yet effective framework that introduces contemporary semi-supervised learning techniques into the realm of adversarial training. By enhancing pseudo labels and managing noisy training data more effectively, SNORD showcases impressive, state-of-the-art performance across diverse datasets and labeling budgets, all without the need for pretrained models. Compared to full adversarial supervision, SNORD achieves a 90% relative robust accuracy under epsilon = 8/255 AutoAttack, requiring less than 0.1%, 2%, and 10% labels for CIFAR-10, CIFAR-100, and TinyImageNet-200, respectively. Additional experiments confirm the efficacy of each component and demonstrate the adaptability of integrating SNORD with existing adversarial pretraining strategies to further bolster robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12946 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation Wu, Tsung-Han Su, Hung-Ting Chen, Shang-Tse Hsu, Winston H. Machine Learning Computer Vision and Pattern Recognition The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training. To explore the possibility of tackling more complicated tasks with even lower labeling budgets, unlike prior approaches that rely on robust pretrained models, we present SNORD - a simple yet effective framework that introduces contemporary semi-supervised learning techniques into the realm of adversarial training. By enhancing pseudo labels and managing noisy training data more effectively, SNORD showcases impressive, state-of-the-art performance across diverse datasets and labeling budgets, all without the need for pretrained models. Compared to full adversarial supervision, SNORD achieves a 90% relative robust accuracy under epsilon = 8/255 AutoAttack, requiring less than 0.1%, 2%, and 10% labels for CIFAR-10, CIFAR-100, and TinyImageNet-200, respectively. Additional experiments confirm the efficacy of each component and demonstrate the adaptability of integrating SNORD with existing adversarial pretraining strategies to further bolster robustness. |
| title | Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.12946 |