Internet of Vehicles (IoV) is a part of IOT which gradually emerged by connecting vehicles and infrastructure to interconnected systems that handle cyber vulnerabilities. To address the difficulty of detecting these intrusions, CICIoV 2024 dataset, which included 1,408,219 rows and 12 attributes. The dataset had a high degree of class imbalance that was dealt with using the SMOTE (synthetic minority oversampling technique). This SMOTE increased the data set to 7,342,422 rows, which has better balance of predictable and abnormal traffic. To do this, use different machine learning techniques such as Naive Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), k-nearest neighbors (k-NN), Logistic Regression (LR), LightGBM, and Principal Component Analysis (PCA). We used various boosting algorithms, including AdaBoost, CatBoost, LightGBM and XGBoost, to detect cyber risk in the IoV environment environment. The models were analyzed using accuracy, precision, recall and F1 score criteria. This shows that RF, K-NN, LR, LightGBM, XGBoost, AdaBoost, and CatBoost detected cyber risks. These algorithms has improve the security of IoV networks by efficiently detecting intrusions.