In the evolving landscape of the Internet of Vehicles (IoV), ensuring robust security at the edge of the network is paramount. This study addresses the critical need for robust security in edge computing environments within the IoV. We conduct an in-depth evaluation of a wide range of machine learning algorithms - including Random Forest, Gradient Boosting, Support Vector Machines (SVMs), K-Nearest Neighbors (KNN), Decision Trees, AdaBoost, Logistic Regression, and XGBoost - for cyber-attack classification in IoV systems. Utilizing the ML-EdgeIIoT-dataset, we assess these algorithms against key metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. Our findings reveal that ensemble methods, particularly Gradient Boosting and XGBoost, demonstrate superior performance in accurately detecting IoV cyber threats, effectively balancing computational demands. The study highlights the importance of strategically selecting algorithms to meet the specific security needs of the dynamic IoV environment. The results not only enhance the current understanding of IoV security but also pave the way for future research to develop adaptive, efficient, and precise security mechanisms for real-time IoV applications.