论文标题
训练的彩色噪声注入对抗性强大的神经网络
Colored Noise Injection for Training Adversarially Robust Neural Networks
论文作者
论文摘要
即使深度学习在各种任务上表现出无与伦比的表现，但神经网络已被证明容易受到输入的小对抗扰动的影响，从而导致大量性能降级。在这项工作中，我们将在对抗训练（PNI）期间向网络的重量和激活中添加白色高斯噪声的想法将其注入有色噪声，以防止对常见的白色盒子和黑色盒子的攻击。我们表明，在CIFAR-10和CIFAR-100数据集上，我们的方法优于PNI和以前的各种方法。此外，我们还提供了对所选配置合理的提议方法的广泛消融研究。
Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that lead to significant performance degradation. In this work we extend the idea of adding white Gaussian noise to the network weights and activations during adversarial training (PNI) to the injection of colored noise for defense against common white-box and black-box attacks. We show that our approach outperforms PNI and various previous approaches in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets. In addition, we provide an extensive ablation study of the proposed method justifying the chosen configurations.
