CamPI：通过相机电源信号注入实现物理对抗样本
CamPI: Physical Adversarial Examples through Camera Power Signal Injection
揭示了一种全新的物理对抗攻击面：通过向相机供电线路注入调制信号，在成像中产生不可见的结构性条纹扰动，并给出白盒/黑盒端到端优化注入参数的方法；对做物理世界视觉系统安全评测的研究者，这提供了一个可仿真的注入扰动模型和一套可复用的攻击参数优化流程。
原文依据 we reveal a new attack surface that generates invisible adversarial samples by injecting signals into the camera's power supply
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论物理对抗样本对现实世界的计算机视觉系统构成切实威胁。现有工作主要通过粘贴补丁或向目标投射光来生成物理对抗样本，这些方式通常可见，并会暴露恶意意图。在本工作中，我们揭示了一种新的攻击面：通过向相机电源注入信号来生成不可见的对抗样本。我们分析了向相机注入结构性条纹图案的机制，并证明了通过信号调制实现可控细粒度注入的可行性。我们构建了一个仿真模型来模拟物理注入的扰动，并提出了白盒与黑盒设置下的端到端优化方法，用于生成注入信号参数。我们在七个分类模型上进行了仿真评估，并使用优化后的信号开展了物理信号注入实验。结果表明，通过相机电源信号注入生成的物理对抗样本能够破坏计算机视觉性能。我们的工作为物理对抗样本引入了一种新方法，凸显了在物理世界中保障计算机视觉系统安全的必要性。
英文原文摘要 1243 字符
Physical adversarial examples pose a concrete threat to real-world computer vision systems. Existing works mainly generate physical adversarial examples by affixing patches or projecting light onto targets, which are usually visible and can expose the malicious intention. In this work, we reveal a new attack surface that generates invisible adversarial samples by injecting signals into the camera's power supply. We analyze the mechanism of injecting structural stripe patterns into cameras and demonstrate the feasibility of controllable fine-grained injection with signal modulation. We develop a simulation model to emulate the physically injected perturbation, and propose end-to-end optimization methodologies in both white-box and black-box settings to generate the injection signal parameters. We perform a simulated evaluation across seven classification models and carry out physical signal injection experiments with optimized signals. The results show that physical adversarial examples generated through camera power signal injection can disrupt computer vision performance. Our work introduces a new methodology for physical adversarial examples, emphasizing the need for securing computer vision systems in the physical world.