Deep Neural Networks (DNNs) are being used to solve a wide range of problems in many domains including safety-critical domains like self-driving cars and medical imagery. DNNs suffer from vulnerability against adversarial attacks. In the past few years, numerous approaches have been proposed to tackle this problem by training networks using adversarial training. Almost all the approaches generate adversarial examples for the entire training dataset, thus increasing the training time drastically. We show that we can decrease the training time for any adversarial training algorithm by using only a subset of training data for adversarial training. To select the subset, we filter the adversarially-prone samples from the training data. We perform a simple adversarial attack on all training examples to filter this subset. In this attack, we add a small perturbation to each pixel and a few grid lines to the input image. We perform adversarial training on the adversarially-prone subset and mix it with vanilla training performed on the entire dataset. Our results show that when our method-agnostic approach is plugged into FGSM, we achieve a speedup of 3.52x on MNIST and 1.98x on the CIFAR-10 dataset with comparable robust accuracy. We also test our approach on state-of-the-art Free adversarial training and achieve a speedup of 1.2x in training time with a marginal drop in robust accuracy on the ImageNet dataset.
翻译:深度神经网络(DNNs)被用于许多领域的问题解决,包括自动驾驶汽车和医学图像等安全关键领域。DNNs容易受到对抗攻击的影响。过去几年中,已经提出了许多方法来通过对抗训练来解决这个问题。几乎所有的方法都生成整个训练数据集的对抗性示例,从而极大地增加了训练时间。我们展示了一个简单的方法,即只使用训练数据的子集进行对抗性训练,以减少任何对抗训练算法的训练时间。我们通过过滤出对抗倾向性样本来选择子集。我们对所有训练样本进行简单的对抗性攻击以过滤这个子集。在攻击中,我们对输入图像中的每个像素和几个网格线都添加了一个小扰动。我们对这些对抗倾向性样本进行对抗性训练,然后将其与整个数据集上进行的普通训练混合。我们的结果表明,当我们的方法通用的方法被嵌入到FGSM中时,我们在MNIST数据集上实现了3.52倍的加速,CIFAR-10数据集上实现了1.98倍的加速,并且具有相当的健壮准确性。我们还在ImageNet数据集上测试了我们的方法,并在一定的健壮准确性下实现了1.2倍的训练时间加速,这是最先进的Free对抗性训练。