RFLA：物理世界中一种隐蔽的反射光对抗攻击
RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World
AI总结：
针对物理对抗补丁显眼、光学攻击白天效果弱的问题，提出基于圆形反射光建模并优化几何形状、颜色与透明度的 RFLA，实现数字与物理环境下高隐蔽、超过99%成功率的攻击。
摘要：
针对深度神经网络（DNN）的物理对抗攻击近来受到越来越多的关注。当前主流的物理攻击使用打印的对抗补丁或伪装来改变目标物体的外观。然而，这些方法会产生显眼的对抗图案，隐蔽性较差。另一种可在物理环境中部署的攻击是光学攻击，其特点是具有隐蔽性，但在白天有阳光时表现较弱。本文提出一种新型反射光攻击（RFLA），在数字世界和物理世界中均有效且隐蔽；该方法通过在镜子前放置彩色透明塑料片和特定形状的剪纸，在目标物体上形成不同颜色的几何图形。为实现这些目标，我们设计了一个基于圆的通用框架，对目标物体上的反射光进行建模。具体而言，我们优化一个圆（由坐标和半径组成），使其承载由优化角度决定的各种几何形状。几何形状的填充颜色及其相应透明度也会被优化。我们在不同数据集和模型上广泛评估了 RFLA 的有效性。实验结果表明，所提方法在数字世界中的不同数据集和模型上取得了超过 99% 的成功率。此外，我们通过使用阳光或手电筒，在不同物理环境中验证了所提方法的有效性。
英文摘要：
Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches or camouflage to alter the appearance of the target object. However, these approaches generate conspicuous adversarial patterns that show poor stealthiness. Another physical deployable attack is the optical attack, featuring stealthiness while exhibiting weakly in the daytime with sunlight. In this paper, we propose a novel Reflected Light Attack (RFLA), featuring effective and stealthy in both the digital and physical world, which is implemented by placing the color transparent plastic sheet and a paper cut of a specific shape in front of the mirror to create different colored geometries on the target object. To achieve these goals, we devise a general framework based on the circle to model the reflected light on the target object. Specifically, we optimize a circle (composed of a coordinate and radius) to carry various geometrical shapes determined by the optimized angle. The fill color of the geometry shape and its corresponding transparency are also optimized. We extensively evaluate the effectiveness of RFLA on different datasets and models. Experiment results suggest that the proposed method achieves over 99% success rate on different datasets and models in the digital world. Additionally, we verify the effectiveness of the proposed method in different physical environments by using sunlight or a flashlight.
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。
