In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914410029645824 |
|---|---|
| author | Fang, Xiao Gong, Yiming Panev, Stanislav de Melo, Celso Hu, Shuowen Chakraborty, Shayok De la Torre, Fernando |
| author_facet | Fang, Xiao Gong, Yiming Panev, Stanislav de Melo, Celso Hu, Shuowen Chakraborty, Shayok De la Torre, Fernando |
| contents | Deep neural networks (DNNs) have achieved remarkable success in computer vision but remain highly vulnerable to adversarial attacks. Among them, camouflage attacks manipulate an object's visible appearance to deceive detectors while remaining stealthy to humans. In this paper, we propose a new framework that formulates vehicle camouflage attacks as a conditional image-editing problem. Specifically, we explore both image-level and scene-level camouflage generation strategies, and fine-tune a ControlNet to synthesize camouflaged vehicles directly on real images. We design a unified objective that jointly enforces vehicle structural fidelity, style consistency, and adversarial effectiveness. Extensive experiments on the COCO and LINZ datasets show that our method achieves significantly stronger attack effectiveness, leading to more than 38% AP50 decrease, while better preserving vehicle structure and improving human-perceived stealthiness compared to existing approaches. Furthermore, our framework generalizes effectively to unseen black-box detectors and exhibits promising transferability to the physical world. Project page is available at https://humansensinglab.github.io/CtrlCamo |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19456 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing Fang, Xiao Gong, Yiming Panev, Stanislav de Melo, Celso Hu, Shuowen Chakraborty, Shayok De la Torre, Fernando Computer Vision and Pattern Recognition Deep neural networks (DNNs) have achieved remarkable success in computer vision but remain highly vulnerable to adversarial attacks. Among them, camouflage attacks manipulate an object's visible appearance to deceive detectors while remaining stealthy to humans. In this paper, we propose a new framework that formulates vehicle camouflage attacks as a conditional image-editing problem. Specifically, we explore both image-level and scene-level camouflage generation strategies, and fine-tune a ControlNet to synthesize camouflaged vehicles directly on real images. We design a unified objective that jointly enforces vehicle structural fidelity, style consistency, and adversarial effectiveness. Extensive experiments on the COCO and LINZ datasets show that our method achieves significantly stronger attack effectiveness, leading to more than 38% AP50 decrease, while better preserving vehicle structure and improving human-perceived stealthiness compared to existing approaches. Furthermore, our framework generalizes effectively to unseen black-box detectors and exhibits promising transferability to the physical world. Project page is available at https://humansensinglab.github.io/CtrlCamo |
| title | In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.19456 |