Mitigating Version Number Attacks in RPL-Based IoT Networks: A Machine Learning Approach | ||||
| Journal of Engineering Science and Military Technologies | ||||
| Articles in Press, Accepted Manuscript, Available Online from 23 February 2025 | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/ejmtc.2025.344143.1293 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Ammar Ibrahim El sayed ; Mahmoud Abdelaziz  ; Mohamed Hussein Abdelwahab Ahmed; Ashraf D. Elbayoumy
| ||||
| Military Technical College | ||||
| Abstract | ||||
| This paper investigates the Version Number Attack (VNA), a form of Denial of Service (DoS) threat, within the Routing Protocol for Low-Power and Lossy Networks (RPL) in IoT-based Wireless Sensor Networks (WSNs). The study assesses the impact of VNAs across various attack scenarios, including single, double, and triple attacker setups, on critical network performance metrics such as power consumption, packet loss, and delay. Using a simulated WSN environment, datasets are generated under both normal and attack conditions to evaluate network behaviour. A Random Forest machine learning model is employed for feature selection, identifying the most significant metrics for attack detection. The results demonstrate that increasing the number of attackers drastically affects network performance, particularly in power consumption and packet loss, leading to significant degradation in overall network reliability. By providing an in-depth analysis of VNA effects and leveraging machine learning for mitigation, this research contributes to the development of efficient security strategies for IoT networks operating under RPL protocols. | ||||
| Keywords | ||||
| IoT; RPL; VNA; DoS; ML | ||||
|
Statistics Article View: 160 |
||||
