Authenticated Encryption Based on Chaotic Neural Networks and Duplex Construction

In this paper, we propose, implement and analyze an Authenticated Encryption with Associated Data Scheme (AEADS) based on the Modified Duplex Construction (MDC) that contains a chaotic compression function (CCF) our neural network revised (CNNR). Unlike standard duplex construction (SDC), in MDC there are two phases: initialization phase duplexing phase, each contain CNNR formed by single layer, followed set of non-linear functions. The is implemented variants width, i.e., 512 1024 bits. We tested proposed scheme against different cryptanalytic attacks. fact, evaluated key message sensitivity, collision resistance analysis diffusion effect. Additionally, AEADS using statistical tests such as NIST, Histogram, chi-square, entropy, correlation analysis. experimental results obtained security performance system notable can then be used to protect data authenticate their sources.