Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915361802158080 |
|---|---|
| author | Kazoom, Roie Birman, Raz Hadar, Ofer |
| author_facet | Kazoom, Roie Birman, Raz Hadar, Ofer |
| contents | The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against such attacks. Optimized adversarial patches were generated and placed in sensitive image regions, by applying EigenCAM and grid search to determine optimal placement. We tested several defenses, including Segment and Complete (SAC), Inpainting, and Latent Diffusion Models. Our pipeline comprises three main stages: patch application, object detection, and defense analysis. Results indicate that adversarial patches reduce average detection confidence by 22.06\%. Defenses restored confidence levels by 3.45\% (SAC), 5.05\% (Inpainting), and significantly improved them by 26.61\%, which even exceeds the original accuracy levels, when using the Latent Diffusion Model, highlighting its superior effectiveness in mitigating the effects of adversarial patches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12988 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks Kazoom, Roie Birman, Raz Hadar, Ofer Computer Vision and Pattern Recognition Artificial Intelligence The widespread adoption of computer vision systems has underscored their susceptibility to adversarial attacks, particularly adversarial patch attacks on object detectors. This study evaluates defense mechanisms for the YOLOv5 model against such attacks. Optimized adversarial patches were generated and placed in sensitive image regions, by applying EigenCAM and grid search to determine optimal placement. We tested several defenses, including Segment and Complete (SAC), Inpainting, and Latent Diffusion Models. Our pipeline comprises three main stages: patch application, object detection, and defense analysis. Results indicate that adversarial patches reduce average detection confidence by 22.06\%. Defenses restored confidence levels by 3.45\% (SAC), 5.05\% (Inpainting), and significantly improved them by 26.61\%, which even exceeds the original accuracy levels, when using the Latent Diffusion Model, highlighting its superior effectiveness in mitigating the effects of adversarial patches. |
| title | Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.12988 |