论文标题
使用生成模型合成无限制的假阳性对象
Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
论文作者
论文摘要
对抗性示例是神经网络错误分类的数据点。最初，对抗性示例仅限于在给定图像中添加小的扰动。最近的工作介绍了不受限制的对抗示例的广义概念，但对增加的扰动而没有限制。在本文中，我们介绍了一个新的攻击类别，这些攻击创建了不受限制的对抗示例以进行对象检测。我们的关键思想是生成与目标对象检测器确定的类无关的对抗对象。与以前的攻击不同，我们使用现成的生成对抗网络（GAN），而无需进行任何进一步的培训或修改。我们的方法包括在GAN的潜在正常空间上搜索目标对象检测器错误识别的对抗对象。我们使用徽标生成的IWGAN-LC和经过CIFAR-10训练的SNGAN，对常用的R-CNN RESNET-101，INCEPTION V2和SSD MOBILENET V1对象检测器进行评估。经验结果表明，生成的对抗对象与gan产生的非对抗对象没有区别，可在物理世界中转移和鲁棒在物理世界之间。这是研究无限制的假阳性对抗示例以进行对象检测的第一项。
Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unrestricted adversarial examples, without limits on the added perturbations. In this paper, we introduce a new category of attacks that create unrestricted adversarial examples for object detection. Our key idea is to generate adversarial objects that are unrelated to the classes identified by the target object detector. Different from previous attacks, we use off-the-shelf Generative Adversarial Networks (GAN), without requiring any further training or modification. Our method consists of searching over the latent normal space of the GAN for adversarial objects that are wrongly identified by the target object detector. We evaluate this method on the commonly used Faster R-CNN ResNet-101, Inception v2 and SSD Mobilenet v1 object detectors using logo generative iWGAN-LC and SNGAN trained on CIFAR-10. The empirical results show that the generated adversarial objects are indistinguishable from non-adversarial objects generated by the GANs, transferable between the object detectors and robust in the physical world. This is the first work to study unrestricted false positive adversarial examples for object detection.
