Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
This addresses security threats in real-time systems by providing a fast and accurate defense against adversarial attacks, though it is incremental as it builds on existing VAE-based approaches.
The paper tackles the vulnerability of deep neural networks to adversarial attacks by proposing Defense-VAE, a method that uses a variational autoencoder to remove adversarial perturbations from images, achieving superior defense accuracy and being 50x faster than Defense-GAN.
Deep neural networks (DNNs) have been enormously successful across a variety of prediction tasks. However, recent research shows that DNNs are particularly vulnerable to adversarial attacks, which poses a serious threat to their applications in security-sensitive systems. In this paper, we propose a simple yet effective defense algorithm Defense-VAE that uses variational autoencoder (VAE) to purge adversarial perturbations from contaminated images. The proposed method is generic and can defend white-box and black-box attacks without the need of retraining the original CNN classifiers, and can further strengthen the defense by retraining CNN or end-to-end finetuning the whole pipeline. In addition, the proposed method is very efficient compared to the optimization-based alternatives, such as Defense-GAN, since no iterative optimization is needed for online prediction. Extensive experiments on MNIST, Fashion-MNIST, CelebA and CIFAR-10 demonstrate the superior defense accuracy of Defense-VAE compared to Defense-GAN, while being 50x faster than the latter. This makes Defense-VAE widely deployable in real-time security-sensitive systems. Our source code can be found at https://github.com/lxuniverse/defense-vae.