Hybrid Flamingo Search and Ant Colony Optimization for Real-Time Intrusion Detection in IoT Networks

Abstract

Real-time threat detection in Internet of Things (IoT) networks is addressed in this research using a unique hybrid method combining Ant Colony Optimization (ACO) and Flamingo Search Algorithm (FSA). IoT ecosystems' natural resource limits and diversity call for optimization strategies that may quickly identify hazards while reducing computing overhead. Our FSA-ACO hybrid builds an adaptable, resource-efficient detection framework by combining the global search powers of flamingo search with the local optimization power of ant colony algorithms. Experimental results show a 23% increase in detection accuracy and a 47% decrease in false positives when compared to conventional machine learning methods. With little computational cost, the proposed model identifies zero-day attacks with 96.8% accuracy, making it fit for use in resource-constrained IoT contexts. These findings draw attention to the possible use of bio-inspired hybridization to solve the developing security issues in complex IoT ecosystems.