Using GAN-Based Encryption to Secure Digital Images With Reconstruction Through Customized Super Resolution Network

Abstract

Unlike traditional encryption methods, Generative Adversarial Network (GAN)-based methods possess a high level of security for digital images. Many existing simple encryption methods may be less secure than expected and have high storage costs. This paper proposes a GAN-based encryption method to secure digital images, solving these problems. First, a random sequence generator using a GAN with cross-coupled logistics and a Henon map is generated to encrypt an image. Next, the encrypted image is downsampled into one-fourth of the original size and sent to the receiver. Finally, image reconstruction uses a Customized Super Resolution Network (CSRNet) rather than decompressing the image at the receiver side. Our extensive experimental results demonstrate that the proposed method achieves NPCR, UACI, entropy, PSNR and SSIM up to 0.99604, 0.33460, 7.9993, 37.0462 dB and 0.94561, respectively. Further, our encryption method achieves up to 75% faster than the recent methods when evaluated on two standard datasets. Therefore, the proposed GAN-Based solution can possess a high level of security and save sufficient storage space for any practical application.