External Sinkhole Attack Detection in Large-Scale WSNs Using Metaheuristic Feature Selection

2026-08-15

AI Summary

This study addresses the threat of external blackhole attacks in large-scale wireless sensor networks by proposing a metaheuristic feature selection method based on swarm intelligence optimization. The approach achieves efficient dimensionality reduction and attack detection through intelligent search mechanisms, effectively overcoming performance bottlenecks associated with high-dimensional data. Experimental evaluations in a 2,000-node simulation environment demonstrate that the model reduces the feature set from 16 to 8 dimensions while maintaining a detection accuracy of 0.997. These results significantly enhance WSN security efficacy and validate the innovative application of metaheuristic algorithms in cybersecurity feature engineering, offering a robust solution for intrusion detection in resource-constrained network environments.

Abstract

Sinkhole attacks in large-scale wireless sensor networks (WSNs) pose a serious threat to network functionality. This paper presents a metaheuristic feature selection for sinkhole attack detection using the bee swarm optimization (BSO) algorithm. In an external sinkhole attack simulation with 2000 nodes deployed over a 3000 $\times$ 3000 m$^2$ field, the proposed method achieves a detection accuracy of 0.997 while reducing the 16-feature set to eight features.

Problem

• Sinkhole Attack
• Wireless Sensor Networks
• Attack Detection
• Large-Scale WSNs

Innovation

• Bee Swarm Optimization
• Metaheuristic Feature Selection
• Sinkhole Attack Detection
• Wireless Sensor Networks