ADVENT: Attack/Anomaly Detection in VANETs

In the domain of Vehicular Ad hoc Networks (VANETs), where the imperative of having a real-world malicious detector capable of detecting attacks in real-time and unveiling their perpetrators is crucial, our study introduces a system with this goal. This system is designed for real-time detection of malicious behavior, addressing the critical need to first identify the onset of attacks and subsequently the responsible actors. Prior work in this area have never addressed both requirements, which we believe are necessary for real world deployment, simultaneously. By seamlessly integrating statistical and machine learning techniques, the proposed system prioritizes simplicity and efficiency. It excels in swiftly detecting attack onsets with a remarkable F1-score of 99.66%, subsequently identifying malicious vehicles with an average F1-score of approximately 97.85%. Incorporating federated learning in both stages enhances privacy and improves the efficiency of malicious node detection, effectively reducing the false negative rate.

A Boosting Approach to Constructing an Ensemble Stack

An approach to evolutionary ensemble learning for classification is proposed in which boosting is used to construct a stack of programs. Each application of boosting identifies a single champion and a residual dataset, i.e. the training records that thus far were not correctly classified. The next program is only trained against the residual, with the process iterating until some maximum ensemble size or no further residual remains. Training against a residual dataset actively reduces the cost of training. Deploying the ensemble as a stack also means that only one classifier might be necessary to make a prediction, so improving interpretability. Benchmarking studies are conducted to illustrate competitiveness with the prediction accuracy of current state-of-the-art evolutionary ensemble learning algorithms, while providing solutions that are orders of magnitude simpler. Further benchmarking with a high cardinality dataset indicates that the proposed method is also more accurate and efficient than XGBoost.