AEGAN: Generating imperceptible face synthesis via autoencoder‐based generative adversarial network

• Published in: Computer animation and virtual worlds Vol. 34; no. 3-4
• Main Authors: Che, Aolin, Yang, Jing‐Hua, Guo, Cai, Dai, Hong‐Ning, Xie, Haoran, Li, Ping
• Format: Journal Article
• Language: English
• Published: Chichester Wiley Subscription Services, Inc 01.05.2023
• Subjects: Artificial neural networks; autoencoder; face image protection; Face recognition; Generative adversarial networks; Human performance; Image enhancement; Image quality; Interpolation; Modules; multi‐head attention; Social networks; Synthesis; Visual effects
• ISSN: 1546-4261; 1546-427X
• DOI: 10.1002/cav.2160

Face recognition (FR) systems based on convolutional neural networks have shown excellent performance in human face inference. However, some malicious users may exploit such powerful systems to identify others' face images disclosed by victims' social network accounts, consequently obtaining private information. To address this emerging issue, synthesizing face protection images with visual and protective effects is essential. However, existing face protection methods encounter three critical problems: poor visual effect, limited protective effect, and trade‐off between visual and protective effects. To address these challenges, we propose a novel face protection approach in this article. Specifically, we design a generative adversarial network (GAN) framework with an autoencoder (AEGAN) as the generator to synthesize the protection images. It is worth noting that we introduce an interpolation upsampling module in the decoder in order to let the synthesized protection images evade recognition by powerful convolution‐based FR systems. Furthermore, we introduce an attention module with a perceptual loss in AEGAN to enhance the visual effects of synthesized images by AEGAN. Extensive experiments have shown that AEGAN not only can maintain the comfortable visual quality of synthesized images but also prevent the recognition of commercial FR systems, including Baidu and iKLYTEK. This article designs a generative adversarial network framework with autoencoder for face protection. We introduce an interpolation upsampling in the decoder to ensure synthesized protection images evade recognition via powerful face recognition systems. We devise an attention module with a perceptual loss to enhance the visual effects of synthesized images.