PPD: Permutation Phase Defense Against Adversarial Examples in Deep Learning
This addresses the vulnerability of deep neural networks to adversarial attacks, which is a critical security issue for AI systems, though it appears incremental as it builds on existing defense strategies.
The paper tackled the problem of adversarial examples in deep learning by proposing Permutation Phase Defense (PPD), a novel method that combines random permutation with Fourier transform phase components, achieving state-of-the-art robustness on MNIST and CIFAR-10 datasets against powerful attacks.
Deep neural networks have demonstrated cutting edge performance on various tasks including classification. However, it is well known that adversarially designed imperceptible perturbation of the input can mislead advanced classifiers. In this paper, Permutation Phase Defense (PPD), is proposed as a novel method to resist adversarial attacks. PPD combines random permutation of the image with phase component of its Fourier transform. The basic idea behind this approach is to turn adversarial defense problems analogously into symmetric cryptography, which relies solely on safekeeping of the keys for security. In PPD, safe keeping of the selected permutation ensures effectiveness against adversarial attacks. Testing PPD on MNIST and CIFAR-10 datasets yielded state-of-the-art robustness against the most powerful adversarial attacks currently available.