Corrupting Data to Remove Deceptive Perturbation: Using Preprocessing Method to Improve System Robustness

TL;DR

This paper proposes a preprocessing method that corrupts and then recovers images to enhance neural network robustness against deceptive perturbations, demonstrating improved classification performance.

Contribution

Introducing a novel preprocessing approach using a SARGAN-based recovery process to improve neural network robustness against adversarial noise.

Findings

SARGAN can effectively denoise corrupted images.

The method improves classification accuracy on adversarially perturbed images.

Preprocessing enhances robustness of naturally trained networks.

Abstract

Although deep neural networks have achieved great performance on classification tasks, recent studies showed that well trained networks can be fooled by adding subtle noises. This paper introduces a new approach to improve neural network robustness by applying the recovery process on top of the naturally trained classifier. In this approach, images will be intentionally corrupted by some significant operator and then be recovered before passing through the classifiers. SARGAN -- an extension on Generative Adversarial Networks (GAN) is capable of denoising radar signals. This paper will show that SARGAN can also recover corrupted images by removing the adversarial effects. Our results show that this approach does improve the performance of naturally trained networks.