Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2002.03339 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914675684278272 |
|---|---|
| author | Liu, Jiangchao Chen, Liqian Mine, Antoine Wang, Ji |
| author_facet | Liu, Jiangchao Chen, Liqian Mine, Antoine Wang, Ji |
| contents | Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs are much larger than that of misclassified inputs which include adversarial examples, especially those from strong adversarial attacks. Another observation is that the robustness radii of correctly classified inputs often follow a normal distribution. Based on these two observations, we propose to validate inputs for neural networks via runtime local robustness verification. Experiments show that our approach can protect neural networks from adversarial examples and improve their accuracies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2002_03339 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Input Validation for Neural Networks via Runtime Local Robustness Verification Liu, Jiangchao Chen, Liqian Mine, Antoine Wang, Ji Machine Learning F.3.1 Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly classified inputs are much larger than that of misclassified inputs which include adversarial examples, especially those from strong adversarial attacks. Another observation is that the robustness radii of correctly classified inputs often follow a normal distribution. Based on these two observations, we propose to validate inputs for neural networks via runtime local robustness verification. Experiments show that our approach can protect neural networks from adversarial examples and improve their accuracies. |
| title | Input Validation for Neural Networks via Runtime Local Robustness Verification |
| topic | Machine Learning F.3.1 |
| url | https://arxiv.org/abs/2002.03339 |