论文标题
另一个中级攻击
Yet Another Intermediate-Level Attack
论文作者
论文摘要
对抗性示例在深神经网络（DNN）模型中的可传递性是一系列黑盒攻击的关键。在本文中，我们提出了一种增强基线对抗示例的黑盒可传递性的新方法。通过建立中间级别差异的线性映射（在一组对抗输入及其良性对应物之间）来预测诱发的对抗性损失，我们的目标是充分利用多步基线攻击的优化程序。我们进行了广泛的实验，以验证方法对CIFAR-100和Imagenet的有效性。实验结果表明，它的表现要优于先前的最新面貌。我们的代码位于https://github.com/qizhangli/ila-plus-plus。
The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial examples. By establishing a linear mapping of the intermediate-level discrepancies (between a set of adversarial inputs and their benign counterparts) for predicting the evoked adversarial loss, we aim to take full advantage of the optimization procedure of multi-step baseline attacks. We conducted extensive experiments to verify the effectiveness of our method on CIFAR-100 and ImageNet. Experimental results demonstrate that it outperforms previous state-of-the-arts considerably. Our code is at https://github.com/qizhangli/ila-plus-plus.
