XGSybil :A Framework for Modeling and Identifying Sybil Attacks in Intelligent Transportation Systems
Hemanth S Patel, Mohd Faizan Khan, Aysha Rahbar, S Nagasundari, N.P. Yashwanth · 2025
With the increasing adoption of autonomous vehicles, ensuring the security of Vehicular Ad-Hoc Networks (VANETs) is critical to maintaining road safety and efficiency. Among the potential threats, Sybil attacks pose a significant challenge by enabling malicious vehicles to illegitimately assume multiple identities, disrupting communication and causing traffic mismanagement. This paper addresses the simulation and detection of Sybil attacks in Intelligent Transportation systems using a combination of network simulation and machine learning. Realistic traffic environments are replicated using tools such as OpenStreetMap, SUMO, and OMNeT++, and attack scenarios are simulated to generate datasets. A machine learning model, trained on these datasets, detects Sybil attacks by analyzing vehicle acceleration and behavioral patterns. The proposed approach successfully identifies malicious nodes, invalidates fraudulent messages, and mitigates their impact, thereby enhancing the security and reliability of autonomous vehicle networks. This study provides a robust framework for Sybil attack detection and contributes to the broader field of secure intelligent transportation systems.