arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.06247cs.AI
收藏

光学对抗攻击

Optical Adversarial Attack

Purdue University(普渡大学)

Abhiram Gnanasambandam, Alex M. Sherman, Stanley H. Chan

摘要:

介绍了光学对抗攻击(OPAD)。OPAD是物理空间中的对抗攻击,旨在欺骗图像分类器而不物理接触对象(例如,移动或绘制对象)。OPAD的原理是使用结构照明来改变目标物体的外观。该系统由一台低成本投影仪、一台摄像机和一台计算机组成。该问题的挑战是投影仪的辐射响应的非线性和场景的空间变化的光谱响应。在传统方法中生成的攻击在这种设置中不起作用,除非它们被校准以补偿这种投影仪-相机模型。提出的解决方案将投影仪-摄像机模型引入到对抗攻击优化中,推导出一种新的攻击公式。实验结果证明了该方法的有效性。它表明,OPAD可以光学攻击一个真正的3D对象在存在的背景照明的白盒,黑盒,有针对性的,和非有针对性的攻击。理论分析量化的基本性能限制的系统。

英文摘要:

We introduce OPtical ADversarial attack (OPAD). OPAD is an adversarial attack in the physical space aiming to fool image classifiers without physically touching the objects (e.g., moving or painting the objects). The principle of OPAD is to use structured illumination to alter the appearance of the target objects. The system consists of a low-cost projector, a camera, and a computer. The challenge of the problem is the non-linearity of the radiometric response of the projector and the spatially varying spectral response of the scene. Attacks generated in a conventional approach do not work in this setting unless they are calibrated to compensate for such a projector-camera model. The proposed solution incorporates the projector-camera model into the adversarial attack optimization, where a new attack formulation is derived. Experimental results prove the validity of the solution. It is demonstrated that OPAD can optically attack a real 3D object in the presence of background lighting for white-box, black-box, targeted, and untargeted attacks. Theoretical analysis is presented to quantify the fundamental performance limit of the system.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑