Machine Learning-Enhanced Hybrid Source Location Privacy Protocol for Improved Security and Network Longevity in IoT Networks

Abstract

Efficient routing in IoT networks is critical for optimizing data transmission while addressing the inherent challenges of energy consumption, scalability, and resilience. Common routing techniques, such as flooding, tree-based, cluster-based, and geographic routing, each present unique advantages and limitations regarding energy efficiency, network congestion, and fault tolerance. In parallel, source location privacy protection (SLPP) has emerged as a pivotal concern in IoT applications like surveillance and environmental monitoring, where adversaries may exploit transmission patterns to identify sensitive source nodes. Despite advancements, current issues in SLP in IoT networks include balancing privacy with energy efficiency, ensuring scalability in dense network environments, and providing resilience against increasingly sophisticated adversarial models. Traditional SLP techniques, including phantom routing, random walks, and dummy packet generation, often impose trade-offs between privacy, energy consumption, and network longevity, limiting their practical application in large-scale IoT networks. Additionally, many existing protocols struggle with adapting to dynamic network topologies and fail to adequately address the challenges posed by hotspot formation, which can lead to uneven energy depletion and compromised privacy. Many SLP methods disrupt the Quality of Service (QoS) by introducing delays or reducing throughput, which can hinder the primary functions of IoT applications, particularly in time-sensitive scenarios. A new Hybrid Source Location Privacy (SLP) protocol that effectively integrates random walks, rumor routing, and Greedy Random Walks to obscure source node locations while optimizing energy consumption is implemented to overcome these limitations. The protocol employs a multi-layer grid framework, dynamic cluster head rotations, and phantom nodes to balance energy usage and reduce network hotspots. The new Hybrid SLP confuses adversaries by combining fake packet generation with adaptive routing strategies, enhancing privacy without compromising network performance. Simulations demonstrate that the Hybrid SLP protocol significantly outperforms existing techniques, achieving lower energy consumption, extended network lifetime, and robust privacy protections, making it ideal for privacy-sensitive IoT applications. The proposed Hybrid SLP protocol integrates a machine learning-based anomaly detection system to enhance its performance and security, highlighting the novelty of the proposed work. This novel combination of advanced routing strategies and machine learning strengthens network resilience against various threats.