Context-Aware Misbehavior Detection Scheme for Vehicular Ad Hoc Networks using Sequential Analysis of the Temporal and Spatial Correlation of the Cooperative Awareness Messages

TL;DR

This paper introduces CAMDS, a context-aware misbehavior detection scheme for VANETs that dynamically assesses the consistency of mobility information using sequential analysis, significantly reducing false alarms and improving detection accuracy.

Contribution

The paper presents a novel dynamic, context-aware misbehavior detection method utilizing sequential analysis and statistical filters, addressing the limitations of static threshold-based solutions in VANETs.

Findings

73% reduction in false alarm rate

37% improvement in detection rate

Effective in high dynamic vehicular environments

Abstract

Vehicular ad hoc Networks (VANETs) are emerged mainly to improve road safety, traffic efficiency, and passenger comfort. The performance of most VANET applications relies on the availability of accurate and recent mobility-information, shared by neighboring vehicles. However, sharing false mobility information can disrupt any potential VANET application. Misbehavior detection is an important security component. However, existing misbehavior detection solutions lack considering the high dynamicity of vehicular context which leads to low detection accuracy and high false alarms. The use of predefined and static security thresholds are the main drawbacks of the existing solutions. In this paper, a context-aware misbehavior detection scheme (CAMDS) is proposed using sequential analysis of temporal and spatial properties of mobility information. A dynamic context reference is constructed online and timely updated using statistical techniques. Firstly, the Kalman filter algorithm is used to track the mobility information received from neighboring vehicles. Then, the innovation errors of the Kalman filter are utilized to construct a temporal consistency assessment model for each vehicle using Box-plot. Then, the Hampel filter is used to construct a spatial consistency assessment model that represents the context reference model. Similarly, plausibility assessment reference models are built online and timely updated using the Hampel filter and by utilizing the consistency assessment reference model of neighboring information. Finally, a message is classified as suspicious if its consistency and plausibility scores deviate much from the context reference model. The proposed context-aware scheme achieved a 73% reduction in false Alarm rate while it achieves a 37% improvement in the detection rate. This proves the effectiveness of the proposed scheme compared with the existing static solutions.