Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.01228 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915223086039040 |
|---|---|
| author | haghjooei, Kimia Rezghi, Mansoor |
| author_facet | haghjooei, Kimia Rezghi, Mansoor |
| contents | Deep learning models have achieved remarkable success in computer vision but remain vulnerable to adversarial attacks, particularly in black-box settings where model details are unknown. Existing adversarial attack methods(even those works with key frames) often treat video data as simple vectors, ignoring their inherent multi-dimensional structure, and require a large number of queries, making them inefficient and detectable. In this paper, we propose \textbf{TenAd}, a novel tensor-based low-rank adversarial attack that leverages the multi-dimensional properties of video data by representing videos as fourth-order tensors. By exploiting low-rank attack, our method significantly reduces the search space and the number of queries needed to generate adversarial examples in black-box settings. Experimental results on standard video classification datasets demonstrate that \textbf{TenAd} effectively generates imperceptible adversarial perturbations while achieving higher attack success rates and query efficiency compared to state-of-the-art methods. Our approach outperforms existing black-box adversarial attacks in terms of success rate, query efficiency, and perturbation imperceptibility, highlighting the potential of tensor-based methods for adversarial attacks on video models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01228 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TenAd: A Tensor-based Low-rank Black Box Adversarial Attack for Video Classification haghjooei, Kimia Rezghi, Mansoor Computer Vision and Pattern Recognition Artificial Intelligence Deep learning models have achieved remarkable success in computer vision but remain vulnerable to adversarial attacks, particularly in black-box settings where model details are unknown. Existing adversarial attack methods(even those works with key frames) often treat video data as simple vectors, ignoring their inherent multi-dimensional structure, and require a large number of queries, making them inefficient and detectable. In this paper, we propose \textbf{TenAd}, a novel tensor-based low-rank adversarial attack that leverages the multi-dimensional properties of video data by representing videos as fourth-order tensors. By exploiting low-rank attack, our method significantly reduces the search space and the number of queries needed to generate adversarial examples in black-box settings. Experimental results on standard video classification datasets demonstrate that \textbf{TenAd} effectively generates imperceptible adversarial perturbations while achieving higher attack success rates and query efficiency compared to state-of-the-art methods. Our approach outperforms existing black-box adversarial attacks in terms of success rate, query efficiency, and perturbation imperceptibility, highlighting the potential of tensor-based methods for adversarial attacks on video models. |
| title | TenAd: A Tensor-based Low-rank Black Box Adversarial Attack for Video Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.01228 |