Dataset and Code for Enhancing security detection and mitigation of Sybil Attacks using Hybrid Learning Techniques

The purpose of the VANET-MaliciousNode Dataset is to identify malicious nodes in vehicular ad hoc networks (VANETs) in real time. It provides a realistic dataset for security research in intelligent transportation systems by simulating vehicle mobility, communication behaviors, trust metrics, and attack patterns. The dataset facilitates the creation and assessment of deep learning and machine learning models, especially those tailored for high-mobility settings and VANET security afforded by 5G.
Features
a. Mobility Data: GPS coordinates, vehicle speed, direction, and acceleration.
b. Packet transmission, delay, signal strength, and message retransmission are examples of communication behavior.
c. Trust Metrics: Trust ratings derived on past behavior and node interactions.
d. Indicators of malicious activity include denial-of-service efforts, blackhole attacks, Sybil attacks, and false packet injections.
e. Target Variable (is_malicious): A binary label that indicates if a node behaves suspiciously (0 = benign, 1 = malicious).