TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors
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_ | 1866910908672901120 |
|---|---|
| author | Dimitriu, Adonisz Michaletzky, Tamás Remeli, Viktor |
| author_facet | Dimitriu, Adonisz Michaletzky, Tamás Remeli, Viktor |
| contents | Adversarial attacks threaten the reliability of machine learning models in critical applications like autonomous vehicles and defense systems. As object detectors become more robust with models like YOLOv8, developing effective adversarial methodologies is increasingly challenging. We present Truck Adversarial Camouflage Optimization (TACO), a novel framework that generates adversarial camouflage patterns on 3D vehicle models to deceive state-of-the-art object detectors. Adopting Unreal Engine 5, TACO integrates differentiable rendering with a Photorealistic Rendering Network to optimize adversarial textures targeted at YOLOv8. To ensure the generated textures are both effective in deceiving detectors and visually plausible, we introduce the Convolutional Smooth Loss function, a generalized smooth loss function. Experimental evaluations demonstrate that TACO significantly degrades YOLOv8's detection performance, achieving an AP@0.5 of 0.0099 on unseen test data. Furthermore, these adversarial patterns exhibit strong transferability to other object detection models such as Faster R-CNN and earlier YOLO versions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21443 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors Dimitriu, Adonisz Michaletzky, Tamás Remeli, Viktor Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Adversarial attacks threaten the reliability of machine learning models in critical applications like autonomous vehicles and defense systems. As object detectors become more robust with models like YOLOv8, developing effective adversarial methodologies is increasingly challenging. We present Truck Adversarial Camouflage Optimization (TACO), a novel framework that generates adversarial camouflage patterns on 3D vehicle models to deceive state-of-the-art object detectors. Adopting Unreal Engine 5, TACO integrates differentiable rendering with a Photorealistic Rendering Network to optimize adversarial textures targeted at YOLOv8. To ensure the generated textures are both effective in deceiving detectors and visually plausible, we introduce the Convolutional Smooth Loss function, a generalized smooth loss function. Experimental evaluations demonstrate that TACO significantly degrades YOLOv8's detection performance, achieving an AP@0.5 of 0.0099 on unseen test data. Furthermore, these adversarial patterns exhibit strong transferability to other object detection models such as Faster R-CNN and earlier YOLO versions. |
| title | TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.21443 |