StyleGAN Encoder-Based Attack for Block Scrambled Face Images

TL;DR

This paper introduces a novel attack method using StyleGAN encoders to recover identifiable features from block-scrambled face images, revealing personal information despite encryption.

Contribution

It is the first to utilize StyleGAN encoder-decoder for attacking encrypted face images, focusing on style recovery rather than exact image reconstruction.

Findings

Reconstructed images reveal identifiable features like hair and eye color.

The method discloses personal information from encrypted images.

Experiments on CelebA show perceptual similarity to original images.

Abstract

In this paper, we propose an attack method to block scrambled face images, particularly Encryption-then-Compression (EtC) applied images by utilizing the existing powerful StyleGAN encoder and decoder for the first time. Instead of reconstructing identical images as plain ones from encrypted images, we focus on recovering styles that can reveal identifiable information from the encrypted images. The proposed method trains an encoder by using plain and encrypted image pairs with a particular training strategy. While state-of-the-art attack methods cannot recover any perceptual information from EtC images, the proposed method discloses personally identifiable information such as hair color, skin color, eyeglasses, gender, etc. Experiments were carried out on the CelebA dataset, and results show that reconstructed images have some perceptual similarities compared to plain images.