Report
Learning to Learn from Mistakes: Robust Optimization for Adversarial Noise
| العنوان: | Learning to Learn from Mistakes: Robust Optimization for Adversarial Noise |
|---|---|
| المؤلفون: | Serban, Alex, Poll, Erik, Visser, Joost |
| سنة النشر: | 2020 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Statistics - Machine Learning |
| الوصف: | Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most compelling defense, adversarial training, requires a substantial increase in processing time and it has been shown to overfit on the training data. In this paper, we aim to overcome these limitations by training robust models in low data regimes and transfer adversarial knowledge between different models. We train a meta-optimizer which learns to robustly optimize a model using adversarial examples and is able to transfer the knowledge learned to new models, without the need to generate new adversarial examples. Experimental results show the meta-optimizer is consistent across different architectures and data sets, suggesting it is possible to automatically patch adversarial vulnerabilities. Comment: Published at ICANN 2020 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2008.05247 |
| رقم الانضمام: | edsarx.2008.05247 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |