Is Perceptual Encryption Secure? A Security Benchmark for Perceptual Encryption Methods

Perceptual encryption methods are the key enablers for protecting image privacy for deep learning-based applications in the cloud. In perceptual encryption, the image content is obfuscated such that the deep learning models can work on the obfuscated data. The key advantage of perceptual encryption over holomorphic encryption is that, unlike holomorphic encryption, the feature required by the target deep learning model is preserved in the encrypted data. Therefore, the model is not required to be retrained on the encrypted data. Recently, a significant number of perceptual encryption methods have been proposed in the literature, each improving over the others. In this paper, we perform a detailed security analysis of three best-known perceptual encryption methods, namely, Adversarial Visual Information Hiding, Learnable Encryption, and Encryption-then-Compression methods designed to protect the privacy of images. We proposed a new GAN-based security evaluation framework to successfully reconstruct the original images encrypted by these methods, showing clear security flaws. We conducted extensive experiments using different datasets and deep learning models. The results show significant vulnerabilities in the existing key-based perceptual encryption methods. The source code of our work is available at the given link: https://github.com/umesh-21/Benchmark to perceptual encryption.