论文标题
分析和扩展视频分类的对抗培训
Analysis and Extensions of Adversarial Training for Video Classification
论文作者
论文摘要
对抗训练（AT）是针对对抗性分类系统的对抗性攻击的一种简单而有效的防御，这是基于增强训练设置的攻击，从而最大程度地提高了损失。但是，AT作为视频分类的辩护的有效性尚未得到彻底研究。我们的第一个贡献是表明，为视频生成最佳攻击需要仔细调整攻击参数，尤其是步骤大小。值得注意的是，我们表明，最佳步长随攻击预算线性变化。我们的第二个贡献是表明，在训练时间使用较小的（次优）攻击预算会导致测试时的性能更加强大。根据这些发现，我们提出了三个防御攻击预算的攻击的防御。自适应AT的第一个技术是一种技术，该技术是从随着训练迭代进行的。第二个课程是一项技术，随着训练的迭代进行，攻击预算的增加。第三个生成的AT，与deno的生成对抗网络一起，以提高稳健的性能。 UCF101数据集上的实验表明，所提出的方法可以改善针对多种攻击类型的对抗性鲁棒性。
Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as a defense for video classification has not been thoroughly studied. Our first contribution is to show that generating optimal attacks for video requires carefully tuning the attack parameters, especially the step size. Notably, we show that the optimal step size varies linearly with the attack budget. Our second contribution is to show that using a smaller (sub-optimal) attack budget at training time leads to a more robust performance at test time. Based on these findings, we propose three defenses against attacks with variable attack budgets. The first one, Adaptive AT, is a technique where the attack budget is drawn from a distribution that is adapted as training iterations proceed. The second, Curriculum AT, is a technique where the attack budget is increased as training iterations proceed. The third, Generative AT, further couples AT with a denoising generative adversarial network to boost robust performance. Experiments on the UCF101 dataset demonstrate that the proposed methods improve adversarial robustness against multiple attack types.
