Hard-label based Small Query Black-box Adversarial Attack
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_ | 1866929270510583808 |
|---|---|
| author | Park, Jeonghwan Miller, Paul McLaughlin, Niall |
| author_facet | Park, Jeonghwan Miller, Paul McLaughlin, Niall |
| contents | We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a successful attack. One approach to tackle this drawback is utilising the adversarial transferability between white box surrogate models and black box target model. However, the majority of the methods adopting this approach are soft label based to take the full advantage of zeroth order optimisation. Unlike mainstream methods, we propose a new practical setting of hard label based attack with an optimisation process guided by a pretrained surrogate model. Experiments show the proposed method significantly improves the query efficiency of the hard label based black-box attack across various target model architectures. We find the proposed method achieves approximately 5 times higher attack success rate compared to the benchmarks, especially at the small query budgets as 100 and 250. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06014 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hard-label based Small Query Black-box Adversarial Attack Park, Jeonghwan Miller, Paul McLaughlin, Niall Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition We consider the hard label based black box adversarial attack setting which solely observes predicted classes from the target model. Most of the attack methods in this setting suffer from impractical number of queries required to achieve a successful attack. One approach to tackle this drawback is utilising the adversarial transferability between white box surrogate models and black box target model. However, the majority of the methods adopting this approach are soft label based to take the full advantage of zeroth order optimisation. Unlike mainstream methods, we propose a new practical setting of hard label based attack with an optimisation process guided by a pretrained surrogate model. Experiments show the proposed method significantly improves the query efficiency of the hard label based black-box attack across various target model architectures. We find the proposed method achieves approximately 5 times higher attack success rate compared to the benchmarks, especially at the small query budgets as 100 and 250. |
| title | Hard-label based Small Query Black-box Adversarial Attack |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.06014 |