Attack GAN (AGAN ): A new Security Evaluation Tool for Perceptual Encryption

TL;DR

This paper introduces AGAN, a GAN-based attack that exposes vulnerabilities in perceptual encryption methods, effectively reconstructing original images and serving as a benchmark for evaluating encryption robustness.

Contribution

The paper presents AGAN, a novel GAN-based attack that challenges perceptual encryption methods and extends to traditional encryption techniques, providing a new tool for security evaluation.

Findings

AGAN successfully reconstructs original images from encrypted data.

AGAN exposes vulnerabilities in AV IH, LE, and EtC encryption methods.

The method serves as a benchmark for assessing encryption robustness.

Abstract

Training state-of-the-art (SOTA) deep learning models requires a large amount of data. The visual information present in the training data can be misused, which creates a huge privacy concern. One of the prominent solutions for this issue is perceptual encryption, which converts images into an unrecognizable format to protect the sensitive visual information in the training data. This comes at the cost of a significant reduction in the accuracy of the models. Adversarial Visual Information Hiding (AV IH) overcomes this drawback to protect image privacy by attempting to create encrypted images that are unrecognizable to the human eye while keeping relevant features for the target model. In this paper, we introduce the Attack GAN (AGAN ) method, a new Generative Adversarial Network (GAN )-based attack that exposes multiple vulnerabilities in the AV IH method. To show the adaptability, the AGAN is extended to traditional perceptual encryption methods of Learnable encryption (LE) and Encryption-then-Compression (EtC). Extensive experiments were conducted on diverse image datasets and target models to validate the efficacy of our AGAN method. The results show that AGAN can successfully break perceptual encryption methods by reconstructing original images from their AV IH encrypted images. AGAN can be used as a benchmark tool to evaluate the robustness of encryption methods for privacy protection such as AV IH.