Hybrid Facial Chaotic-based Graphical Encryption Technique for Cloud Environment

Abstract

Pictographic representations are everywhere in this digital world. IoT, Cloud, Fog, and 5G systems are becoming data transfer boosters for each user. In a real-world situation, secure data transmission is critical through open networks. Many conventional cryptosystems are inadequate for graphical data privacy in terms of computational overhead, latency, and more sensitive to the unknown attacks. In this paper, the secured and low-complex chaotic-based facial image cryptosystem has been developed for computer vision image data. The proposed crypto system utilizes the facial features, Lorentz chaotic maps for private keys production during the encoding process and the same is decrypted using the diffusion process. Facial depictions are merged with chaotic maps that are segmented and decrypted with mutual keys. The performance of the proposed hybrid cryptosystem is validated using the standard facial datasets and NCPR, UACI metrics are measured. Entropy and adjacent pixels correlation metrics also evaluated through proposed cryptosystems.