تقرير
Squeeze Training for Adversarial Robustness
| العنوان: | Squeeze Training for Adversarial Robustness |
|---|---|
| المؤلفون: | Li, Qizhang, Guo, Yiwen, Zuo, Wangmeng, Chen, Hao |
| سنة النشر: | 2022 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Cryptography and Security, Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and non-smoothness of normally obtained loss landscapes. Training augmented with adversarial examples (a.k.a., adversarial training) is considered as an effective remedy. In this paper, we highlight that some collaborative examples, nearly perceptually indistinguishable from both adversarial and benign examples yet show extremely lower prediction loss, can be utilized to enhance adversarial training. A novel method is therefore proposed to achieve new state-of-the-arts in adversarial robustness. Code: https://github.com/qizhangli/ST-AT. Comment: Accepted by ICLR 2023 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2205.11156 |
| رقم الأكسشن: | edsarx.2205.11156 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |