Adversarial examples can deceive a deep neural network (DNN) by significantly altering its response with imperceptible perturbations, which poses new potential vulnerabilities as the growing ubiquity of DNNs. However, most of the existing adversarial examples cannot maintain the malicious functionality if we apply an affine transformation on the resultant examples, which is an important measurement to the robustness of adversarial attacks for the practical risks. To address this issue, we propose an affine-invariant adversarial attack which can consistently construct adversarial examples robust over a distribution of affine transformation. To further improve the efficiency, we propose to disentangle the affine transformation into rotations, translations, magnifications, and reformulate the transformation in polar space. Afterwards, we construct an affine-invariant gradient estimator by convolving the gradient at the original image with derived kernels, which can be integrated with any gradient-based attack methods. Extensive experiments on the ImageNet demonstrate that our method can consistently produce more robust adversarial examples under significant affine transformations, and as a byproduct, improve the transferability of adversarial examples compared with the alternative state-of-the-art methods.
翻译:Aversari 实例可以欺骗一个深心神经网络(DNN),通过明显地改变其反应方式,大大改变其反应方式,无法察觉到干扰干扰,从而带来新的潜在脆弱性,如DNN的日益普遍化。然而,如果对由此产生的例子应用折线变形法,大多数现有的对抗性例子都无法维持恶意功能,这是衡量对抗性攻击对实际风险的稳健性的重要尺度。为了解决这一问题,我们建议采用亲和不稳的对立式对立式攻击(DNNN),这种对立式攻击可以持续地构建强力的对准性对准性例子。为了进一步提高效率,我们提议将亲近式转换为旋转、翻译、放大和极地空间的变异性重新组合。之后,我们通过将原始图像图像网的梯度与任何基于梯度的攻击方法结合起来,从而构建出一种偏向性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性的攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性