Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
It addresses the problem of adversarial attacks for machine learning practitioners by providing a flexible defense method that does not require modifying classifiers or assuming attack knowledge, though it is incremental as it builds on existing generative model techniques.
The paper tackles the vulnerability of deep neural networks to adversarial attacks by proposing Defense-GAN, a framework that uses generative models to defend classifiers by finding unperturbed outputs from adversarial images, resulting in consistent effectiveness against various attacks and improvements over existing defenses.
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