A Direct Approach to Robust Deep Learning Using Adversarial Networks

Abstract

Deep neural networks have been shown to perform well in many classical machine learning problems, especially in image classification tasks. However, researchers have found that neural networks can be easily fooled, and they are surprisingly sensitive to small perturbations imperceptible to humans. Carefully crafted input images (adversarial examples) can force a well-trained neural network to provide arbitrary outputs. Including adversarial examples during training is a popular defense mechanism against adversarial attacks. In this paper we propose a new defensive mechanism under the generative adversarial network (GAN) framework. We model the adversarial noise using a generative network, trained jointly with a classification discriminative network as a minimax game. We show empirically that our adversarial network approach works well against black box attacks, with performance on par with state-of-art methods such as ensemble adversarial training and adversarial training with projected gradient descent.

15 pages

Cited by in corpus (18)

• Robust Local Features for Improving the Generalization of Adversarial Training
• Black-Box Adversarial Attack with Transferable Model-based Embedding
• NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
• Adversarial Distributional Training for Robust Deep Learning
• Learning to Defend by Learning to Attack
• AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows
• Medical Image Harmonization Using Deep Learning Based Canonical Mapping: Toward Robust and Generalizable Learning in Imaging
• What do AI algorithms actually learn? - On false structures in deep learning
• Bag of Tricks for Adversarial Training
• A Robust Adversarial Network-Based End-to-End Communications System With Strong Generalization Ability Against Adversarial Attacks
• Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks
• Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
• Learning Diverse-Structured Networks for Adversarial Robustness
• Progressive Defense Against Adversarial Attacks for Deep Learning as a Service in Internet of Things
• Adversarial Feature Desensitization
• Defective Convolutional Networks
• Ensemble Generative Cleaning with Feedback Loops for Defending Adversarial Attacks
• Black-box Adversarial Example Generation with Normalizing Flows