Towards Robust Training of Neural Networks by Regularizing Adversarial Gradients
arXiv:1805.09370
Abstract
In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures. To address this problem and improve the robustness of neural networks, we investigate the fundamental mechanisms behind adversarial examples and propose a novel robust training method via regulating adversarial gradients. The regulation effectively squeezes the adversarial gradients of neural networks and significantly increases the difficulty of adversarial example generation.Without any adversarial example involved, the robust training method could generate naturally robust networks, which are near-immune to various types of adversarial examples. Experiments show the naturally robust networks can achieve optimal accuracy against Fast Gradient Sign Method (FGSM) and C\&W attacks on MNIST, Cifar10, and Google Speech Command dataset. Moreover, our proposed method also provides neural networks with consistent robustness against transferable attacks.
arXiv comment9 pages, 3 figures
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Delving into Transferable Adversarial Examples and Black-box Attacks
- Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
- Extending Defensive Distillation