Adversarial Transformation Networks: Learning to Generate Adversarial Examples
arXiv:1703.09387
Abstract
Multiple different approaches of generating adversarial examples have been proposed to attack deep neural networks. These approaches involve either directly computing gradients with respect to the image pixels, or directly solving an optimization on the image pixels. In this work, we present a fundamentally new method for generating adversarial examples that is fast to execute and provides exceptional diversity of output. We efficiently train feed-forward neural networks in a self-supervised manner to generate adversarial examples against a target network or set of networks. We call such a network an Adversarial Transformation Network (ATN). ATNs are trained to generate adversarial examples that minimally modify the classifier's outputs given the original input, while constraining the new classification to match an adversarial target class. We present methods to train ATNs and analyze their effectiveness targeting a variety of MNIST classifiers as well as the latest state-of-the-art ImageNet classifier Inception ResNet v2.
Cited by in corpus (9)
- UPSET and ANGRI : Breaking High Performance Image Classifiers
- Geometric robustness of deep networks: analysis and improvement
- Learning from Higher-Layer Feature Visualizations
- A geometry-inspired decision-based attack
- Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation
- Thinking Outside the Pool: Active Training Image Creation for Relative Attributes
- Moving Target Defense for Deep Visual Sensing against Adversarial Examples
- Defending Against Adversarial Attacks Using Random Forests
- Evolution Attack On Neural Networks