论文标题
关于加密模型之间对抗性示例的可转移性
On the Transferability of Adversarial Examples between Encrypted Models
论文作者
论文摘要
深度神经网络（DNN）众所周知，很容易受到对抗性例子的影响（AES）。此外，AE具有对抗性可转移性，即为源模型傻瓜（目标）模型生成的AE。在本文中，我们首次研究了为对抗性强大防御的模型的可传递性。为了客观地验证可转让性的属性，使用称为AutoAttack的基准攻击方法评估模型的鲁棒性。在图像分类实验中，使用加密模型的使用不仅是对AE的鲁棒性，而且还可以减少AES在模型的可传递性方面的影响。
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, namely, AEs generated for a source model fool other (target) models. In this paper, we investigate the transferability of models encrypted for adversarially robust defense for the first time. To objectively verify the property of transferability, the robustness of models is evaluated by using a benchmark attack method, called AutoAttack. In an image-classification experiment, the use of encrypted models is confirmed not only to be robust against AEs but to also reduce the influence of AEs in terms of the transferability of models.
