Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN

Abstract

Deep neural networks have been widely deployed in various machine learning tasks. However, recent works have demonstrated that they are vulnerable to adversarial examples: carefully crafted small perturbations to cause misclassification by the network. In this work, we propose a novel defense mechanism called Boundary Conditional GAN to enhance the robustness of deep neural networks against adversarial examples. Boundary Conditional GAN, a modified version of Conditional GAN, can generate boundary samples with true labels near the decision boundary of a pre-trained classifier. These boundary samples are fed to the pre-trained classifier as data augmentation to make the decision boundary more robust. We empirically show that the model improved by our approach consistently defenses against various types of adversarial attacks successfully. Further quantitative investigations about the improvement of robustness and visualization of decision boundaries are also provided to justify the effectiveness of our strategy. This new defense mechanism that uses boundary samples to enhance the robustness of networks opens up a new way to defense adversarial attacks consistently.

References in corpus (15)

• Distilling the Knowledge in a Neural Network
• Explaining and Harnessing Adversarial Examples
• Ensemble Adversarial Training: Attacks and Defenses
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Towards Deep Learning Models Resistant to Adversarial Attacks
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• Countering Adversarial Images using Input Transformations
• Certifying Some Distributional Robustness with Principled Adversarial Training
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
• Understanding and Enhancing the Transferability of Adversarial Examples
• Cascade Adversarial Machine Learning Regularized with a Unified Embedding

Cited by in corpus (6)

• You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
• Medical Image Harmonization Using Deep Learning Based Canonical Mapping: Toward Robust and Generalizable Learning in Imaging
• Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
• ATRO: Adversarial Training with a Rejection Option
• Diminishing the Effect of Adversarial Perturbations via Refining Feature Representation
• HAD-GAN: A Human-perception Auxiliary Defense GAN to Defend Adversarial Examples