Recent research has proved that deep neural networks (DNNs) are vulnerable to adversarial examples, the legitimate input added with imperceptible and well-designed perturbations can fool DNNs easily in the testing stage. However, most of the existing adversarial attacks are difficult to fool adversarially trained models. To solve this issue, we propose an AdaBelief iterative Fast Gradient Sign Method (AB-FGSM) to generalize adversarial examples. By integrating AdaBelief optimization algorithm to I-FGSM, we believe that the generalization of adversarial examples will be improved, relying on the strong generalization of AdaBelief optimizer. To validate the effectiveness and transferability of adversarial examples generated by our proposed AB-FGSM, we conduct the white-box and black-box attacks on various single models and ensemble models. Compared with state-of-the-art attack methods, our proposed method can generate adversarial examples effectively in the white-box setting, and the transfer rate is 7%-21% higher than latest attack methods.
翻译:最近的研究证明,深层神经网络(DNNS)容易受到对抗性实例的伤害,在无法察觉和设计完善的干扰下添加的合法输入在测试阶段很容易愚弄DNS。然而,大多数现有的对抗性攻击难以愚弄敌对性训练模型。为了解决这个问题,我们建议采用Adabelief迭代快速渐进信号方法(AB-FGSM)来概括对抗性实例。通过将Adabelief优化算法纳入I-FGSM,我们认为,将Adabelief优化算法的普及化将得到改善,依靠Adabelief优化法的有力普及化。要验证我们提议的AB-FGSM生成的对抗性例子的有效性和可转移性,我们要对各种单一模型和共同模型进行白箱和黑箱攻击。与最先进的攻击方法相比,我们提出的方法可以在白箱设置中有效地产生对抗性例子,而转移率比最新的攻击方法高出7%-21%。