Adaptive Gradient for Adversarial Perturbations Generation
arXiv:1902.01220
Abstract
Deep Neural Networks have achieved remarkable success in computer vision, natural language processing, and audio tasks.
arXiv admin note: text overlap with arXiv:1901.03706 The formula in Algorithm 1 lacks important representations
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- On the (Statistical) Detection of Adversarial Examples
- Learning with a Strong Adversary
- Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
- Adversarial Manipulation of Deep Representations
- Robustness of classifiers to universal perturbations: a geometric perspective