Vehicular ad hoc network (VANET) is vital for reducing road accidents and traffic congestion in an Intelligent Transportation System (ITS). The decentralized and dynamic nature of VANETs also makes them vulnerable to security threats. Misbehavior of vehicles, such as malicious attacks or misconfigured equipment, can significantly impact the performance and reliability of VANETs. Ensuring the security and privacy of VANETs is of paramount importance. In this context, machine learning has emerged as a promising approach for detecting misbehavior in VANETs. This study provides an overview of the current state-of-the-art in machine learning based misbehavior detection in VANETs. Here we have studied the different machine learning techniques used for detecting misbehavior. We have presented a detailed analysis of the performance of different machine learning algorithms for misbehavior detection in VANETs. We have highlighted the strengths and weaknesses of each approach and identified the factors that can impact the accuracy and efficiency of the detection process. Finally, we have discussed the ongoing research problems and future avenues for machine learning based misbehavior detection in VANETs, such as dealing with the imbalance and diversity of data and enhancing the interpretability and transparency of the ML models.