Secure Cloud-IoT Communication Using Siamese Heterogeneous Neural Architectures

Abstract

The rapid growth of Internet of Things (IoT) technologies and cloud computing infrastructures has transformed modern digital ecosystems by enabling intelligent connectivity, large-scale data analytics, real-time monitoring, and automated decision-making across diverse applicAbstractation domains. Despite these advancements, secure communication between cloud platforms and IoT devices remains a significant challenge due to increasing cyber threats, unauthorized access attempts, data breaches, spoofing attacks, and communication vulnerabilities. Traditional security mechanisms often struggle to provide adaptive protection against evolving attack patterns and heterogeneous communication environments. Recent developments in artificial intelligence and deep learning have demonstrated substantial potential for enhancing cybersecurity through intelligent feature learning and adaptive threat analysis. This research proposes a Secure Cloud-IoT Communication Framework Using Siamese Heterogeneous Neural Architectures (SCIC-SHNA) that integrates cloud communication analytics, Siamese neural learning, heterogeneous feature extraction, adaptive security intelligence, and intelligent threat detection mechanisms. The proposed framework utilizes parallel neural branches to learn similarities and dissimilarities among communication patterns while effectively capturing complex relationships between cloud and IoT network traffic.