通过可控图像编辑对车辆检测器实施野外伪装攻击

摘要

深度神经网络在计算机视觉领域取得了显著成功，但其对抗攻击的脆弱性依然突出。其中伪装攻击通过改变物体的可见外观来欺骗检测器，同时保持对人类观察者的隐蔽性。本文提出一种新框架，将车辆伪装攻击建模为条件图像编辑问题。具体而言，我们探索了图像级和场景级两种伪装生成策略，通过微调ControlNet直接在真实图像上合成伪装车辆。我们设计了统一目标函数，同时保证车辆结构保真度、风格一致性和对抗有效性。在COCO和LINZ数据集上的大量实验表明，本方法实现了显著更强的攻击效果（导致AP50下降超过38%），同时较现有方法能更好地保持车辆结构并提升人类感知的隐蔽性。此外，我们的框架能有效泛化至未见过的黑盒检测器，并展现出良好的物理世界可迁移性。项目页面详见https://humansensinglab.github.io/CtrlCamo

English

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

通过可控图像编辑对车辆检测器实施野外伪装攻击

In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing

摘要

Support