Mitigating version number attacks in RPL-based IoT networks : A machine learning approach | ||||
| Journal of Engineering Science and Military Technologies | ||||
| Volume 9, Issue 2, September 2025, Page 100-114 PDF (1.15 MB) | ||||
| 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 normal and attack conditions to evaluate network behavior. A Random Forest (RF) machine learning (ML) 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. This research contributes to developing efficient security strategies for IoT networks operating under RPL protocols by providing an in-depth analysis of VNA effects and leveraging ML for mitigation. | ||||
| Keywords | ||||
| DoS; IoT; RPL; VNA; ML | ||||
|
Statistics Article View: 178 PDF Download: 4 |
||||
