Revisiting Role of Autoencoders in Adversarial Settings

TL;DR

This paper investigates autoencoders' inherent robustness to adversarial attacks, revealing their potential to use robust features for defense, which could influence future adversarial defense strategies.

Contribution

It uncovers the inherent adversarial robustness of autoencoders and suggests their use of robust features, providing new insights for adversarial defense research.

Findings

Autoencoders exhibit inherent adversarial robustness.

Autoencoders may utilize robust features for defense.

Findings offer new directions for adversarial defense strategies.

Abstract

To combat against adversarial attacks, autoencoder structure is widely used to perform denoising which is regarded as gradient masking. In this paper, we revisit the role of autoencoders in adversarial settings. Through the comprehensive experimental results and analysis, this paper presents the inherent property of adversarial robustness in the autoencoders. We also found that autoencoders may use robust features that cause inherent adversarial robustness. We believe that our discovery of the adversarial robustness of the autoencoders can provide clues to the future research and applications for adversarial defense.