Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models

ICLR 2018  ·  Pouya Samangouei, Maya Kabkab, Rama Chellappa ·

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can cause misclassification of legitimate images. We propose Defense-GAN, a new framework leveraging the expressive capability of generative models to defend deep neural networks against such attacks. Defense-GAN is trained to model the distribution of unperturbed images. At inference time, it finds a close output to a given image which does not contain the adversarial changes. This output is then fed to the classifier. Our proposed method can be used with any classification model and does not modify the classifier structure or training procedure. It can also be used as a defense against any attack as it does not assume knowledge of the process for generating the adversarial examples. We empirically show that Defense-GAN is consistently effective against different attack methods and improves on existing defense strategies. Our code has been made publicly available at https://github.com/kabkabm/defensegan

PDF Abstract ICLR 2018 PDF ICLR 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Adversarial Defense against FGSM Attack MNIST Defense GAN Accuracy 0.8529 # 1
Inference speed 14.80 # 1
Adversarial Defense MNIST Defense GAN Accuracy 0.8529 # 1
Inference speed 14.80 # 1

Methods


No methods listed for this paper. Add relevant methods here