Adaptive Machine Learning‐Driven MFP Algorithm for Trajectory Anomaly Detection in Vehicular Ad‐Hoc Networks

ABSTRACT Vehicular ad‐hoc networks (VANETs) are integral to the realization of intelligent transportation systems (ITS), enabling seamless communication among vehicles. However, VANETs are highly susceptible to trajectory anomalies (TA) arising from malicious activities, sensor malfunctions, or network attacks, which compromise both network security (NS) and traffic management. The high false positive rates (FPR), computational inefficiency, and poor adaptability to adversarial behaviors may result from the implementation of conventional anomaly detection techniques. Because the pre‐defined threshold values or static (FE) Feature Extraction are mostly utilized by those conventional anomaly detection methods. For TA detection in VANET, a novel machine learning‐based mobility feature prediction (ML‐MFP) algorithm was suggested in this study, and this suggested method is effective to resolve those above‐mentioned issues. For the purpose of analyzing vehicular mobility features, including speed, direction, and position, this study also presents the hybrid approach that integrates the supervised learning (SL) with deep learning (DL) techniques with dynamic clustering (DC). In real‐time (RT), the prediction of mobility patterns and deviation detection are effectively executed by the application of recurrent neural network (RNN) with long short‐term memory (LSTM) units. For high‐speed vehicular backgrounds, this method has become effective by this implementation. The issues related to computational overhead, data privacy, and scalability in dense urban networks can be effectively resolved by the integration of lightweight model optimization strategies and privacy‐preserving (PP) federated learning (FL). Extensive simulations using real‐world vehicular datasets demonstrate that the proposed ML‐MFP algorithm achieves high performance, with 98.57% detection accuracy, 97.53% traffic management efficiency, 96.84% network security, 97.17% robustness, and 98.74% anomaly detection. The results validate the effectiveness and practicality of the proposed approach, which enhances VANET security, improves traffic flow, and contributes to the development of intelligent, secure, and efficient transportation systems.