# Robustness Of Saak Transform Against Adversarial Attacks

## TL;DR

This paper explores the robustness of the Saak transform in image classification against adversarial attacks, proposing spectral dimension selection as a denoising strategy to improve resilience.

## Contribution

It introduces a multi-stage Saak transform-based classification system with spectral dimension selection to enhance adversarial robustness in image classification.

## Key findings

- Saak transform domain shows different distributions for clean and adversarial images
- Spectral dimension selection acts as an automatic denoising process
- Experimental results demonstrate improved robustness against attacks

## Abstract

Image classification is vulnerable to adversarial attacks. This work investigates the robustness of Saak transform against adversarial attacks towards high performance image classification. We develop a complete image classification system based on multi-stage Saak transform. In the Saak transform domain, clean and adversarial images demonstrate different distributions at different spectral dimensions. Selection of the spectral dimensions at every stage can be viewed as an automatic denoising process. Motivated by this observation, we carefully design strategies of feature extraction, representation and classification that increase adversarial robustness. The performances with well-known datasets and attacks are demonstrated by extensive experimental evaluations.