attack arXiv Mar 19, 2026 · 18d ago
Xiao Fang, Yiming Gong, Stanislav Panev et al. · Carnegie Mellon University · DEVCOM Army Research Laboratory +1 more
Physical-world camouflage attack synthesizing adversarial vehicle textures via ControlNet fine-tuning, achieving 38% AP50 drop with transferability
Input Manipulation Attack vision
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
cnn Carnegie Mellon University · DEVCOM Army Research Laboratory · Florida State University
ML Security Papers