StyleGAN Encoder-Based Attack for Block Scrambled Face Images
This addresses privacy concerns for users of encrypted face images, though it is incremental as it builds on existing StyleGAN methods.
The paper tackles the problem of attacking block scrambled face images, specifically Encryption-then-Compression (EtC) images, by using a StyleGAN encoder and decoder to recover identifiable styles like hair color and gender, achieving perceptual similarities in reconstructed images on the CelebA dataset.
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.