Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes
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_ | 1866910304163594240 |
|---|---|
| author | Hamidi, Shayan Mohajer Ye, Linfeng |
| author_facet | Hamidi, Shayan Mohajer Ye, Linfeng |
| contents | Deep neural networks (DNNs) could be deceived by generating human-imperceptible perturbations of clean samples. Therefore, enhancing the robustness of DNNs against adversarial attacks is a crucial task. In this paper, we aim to train robust DNNs by limiting the set of outputs reachable via a norm-bounded perturbation added to a clean sample. We refer to this set as adversarial polytope, and each clean sample has a respective adversarial polytope. Indeed, if the respective polytopes for all the samples are compact such that they do not intersect the decision boundaries of the DNN, then the DNN is robust against adversarial samples. Hence, the inner-working of our algorithm is based on learning \textbf{c}onfined \textbf{a}dversarial \textbf{p}olytopes (CAP). By conducting a thorough set of experiments, we demonstrate the effectiveness of CAP over existing adversarial robustness methods in improving the robustness of models against state-of-the-art attacks including AutoAttack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07991 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes Hamidi, Shayan Mohajer Ye, Linfeng Machine Learning Cryptography and Security Deep neural networks (DNNs) could be deceived by generating human-imperceptible perturbations of clean samples. Therefore, enhancing the robustness of DNNs against adversarial attacks is a crucial task. In this paper, we aim to train robust DNNs by limiting the set of outputs reachable via a norm-bounded perturbation added to a clean sample. We refer to this set as adversarial polytope, and each clean sample has a respective adversarial polytope. Indeed, if the respective polytopes for all the samples are compact such that they do not intersect the decision boundaries of the DNN, then the DNN is robust against adversarial samples. Hence, the inner-working of our algorithm is based on learning \textbf{c}onfined \textbf{a}dversarial \textbf{p}olytopes (CAP). By conducting a thorough set of experiments, we demonstrate the effectiveness of CAP over existing adversarial robustness methods in improving the robustness of models against state-of-the-art attacks including AutoAttack. |
| title | Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2401.07991 |