Machine learning-based lightweight block ciphers for resource-constrained internet of things networks: a review

Abstract

The increasing number of internet of things (IoT) devices, wearable technologies, and embedded systems has experienced a significant increase in recent years. This surge has brought attention to the necessity for cryptographic algorithms that are lightweight and capable of providing security in resource-constrained environments. The primary objective of lightweight block ciphers is to provide encryption capabilities with minimal computational overhead and decreased power consumption. As a result, they are particularly well-suited for use on devices that have limited resources. At the same time, machine learning methodologies have evolved into powerful mechanisms for the purposes of prediction, categorization, and system optimization. This study introduces a challenges and issues involved in integrating machine learning techniques with the development of lightweight block ciphers.