Context-Aware Image Denoising with Auto-Threshold Canny Edge Detection to Suppress Adversarial Perturbation

TL;DR

This paper introduces a context-aware image denoising method combining adaptive smoothing and color reduction, effectively reducing adversarial perturbations and enhancing deep neural network robustness.

Contribution

The paper proposes a novel denoising algorithm using auto-threshold Canny edge detection and color reduction to combat adversarial attacks.

Findings

Reduces adversarial perturbations effectively.

Increases classification accuracy under attack.

Enhances robustness of deep CNN models.

Abstract

This paper presents a novel context-aware image denoising algorithm that combines an adaptive image smoothing technique and color reduction techniques to remove perturbation from adversarial images. Adaptive image smoothing is achieved using auto-threshold canny edge detection to produce an accurate edge map used to produce a blurred image that preserves more edge features. The proposed algorithm then uses color reduction techniques to reconstruct the image using only a few representative colors. Through this technique, the algorithm can reduce the effects of adversarial perturbations on images. We also discuss experimental data on classification accuracy. Our results showed that the proposed approach reduces adversarial perturbation in adversarial attacks and increases the robustness of the deep convolutional neural network models.