Colored Noise Injection for Training Adversarially Robust Neural Networks
arXiv:2003.02188
Abstract
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.
References in corpus (11)
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Theoretically Principled Trade-off between Robustness and Accuracy
- Delving into Transferable Adversarial Examples and Black-box Attacks
- Variational Dropout and the Local Reparameterization Trick
- Lookahead Optimizer: k steps forward, 1 step back
- MMA Training: Direct Input Space Margin Maximization through Adversarial Training
- Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets
- Learning to Defend by Learning to Attack
- Defending against Whitebox Adversarial Attacks via Randomized Discretization
- Adversarial Training with Voronoi Constraints
- Training Robust Deep Neural Networks via Adversarial Noise Propagation