Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.15833 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908335397142528 |
|---|---|
| author | Bayer, Jens Becker, Stefan Münch, David Arens, Michael |
| author_facet | Bayer, Jens Becker, Stefan Münch, David Arens, Michael |
| contents | Adversarial patches in computer vision can be used, to fool deep neural networks and manipulate their decision-making process. One of the most prominent examples of adversarial patches are evasion attacks for object detectors. By covering parts of objects of interest, these patches suppress the detections and thus make the target object 'invisible' to the object detector. Since these patches are usually optimized on a specific network with a specific train dataset, the transferability across multiple networks and datasets is not given. This paper addresses these issues and investigates the transferability across numerous object detector architectures. Our extensive evaluation across various models on two distinct datasets indicates that patches optimized with larger models provide better network transferability than patches that are optimized with smaller models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15833 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Network transferability of adversarial patches in real-time object detection Bayer, Jens Becker, Stefan Münch, David Arens, Michael Computer Vision and Pattern Recognition Adversarial patches in computer vision can be used, to fool deep neural networks and manipulate their decision-making process. One of the most prominent examples of adversarial patches are evasion attacks for object detectors. By covering parts of objects of interest, these patches suppress the detections and thus make the target object 'invisible' to the object detector. Since these patches are usually optimized on a specific network with a specific train dataset, the transferability across multiple networks and datasets is not given. This paper addresses these issues and investigates the transferability across numerous object detector architectures. Our extensive evaluation across various models on two distinct datasets indicates that patches optimized with larger models provide better network transferability than patches that are optimized with smaller models. |
| title | Network transferability of adversarial patches in real-time object detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.15833 |