Abstract—With the increase in the number of Internet of Things (IoT) devices and the advantage of edge computing, it has become a crucial issue to make data confidential. In this paper a novel intelligent adaptive cryptographic model termed SecureEdge-IoT that follows the principles of zero trust will be presented to employ a zero-trust approach for the resource limited edge computing networks. Our approach integrates context-aware lightweight encryption and machine learning-based access control mechanisms to be able to protect sensitive data at the edge nodes. The SecureEdge-IoT model applies two algorithms that sync together, called the Adaptive Lightweight Encryption Algorithm (ALEA) and the Dynamic Access Control Protocol (DACP). Experimental results demonstrate that SecureEdge-IoT reduces encryption time by 52%, energy consumption by 49.5%, memory usage by 48.4%, and increases throughput by 77.9% compared to traditional AES-based methods, achieving an overall weighted performance improvement of 23.7%, computed as a weighted composite index of the normalized improvements in encryption time, energy consumption, memory usage, while maintaining equivalent security strength. Statistical analysis at three comparative studies validates the efficiency and effectiveness of proposed model.
 
Keywords—SecureEdge-IoT, zero-trust architecture, intelligent cryptography, edge computing security, adaptive Internet of Things (IoT) protection
 
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).