Autonomous vehicles (AV) have revolutionized the transport industry and an increase in their usage has prompted the need for safeguarding them against security threats. One such threat is False Data Injection (FDI) attack. FDI attacks can manipulate the sensor data and potentially affect the AVs adversely. The proposed framework addresses FDI attack against AVs by leveraging advanced Machine Learning (ML) techniques. Here we discuss various techniques to detect this anomaly and compare them against each other using f1 scores and various performance metrics. Anomaly detection for FDI attacks in AVs is a key field in maintaining the safety, security, and reliability of these systems. Autonomous vehicles are dependent on sensor data, control algorithms, communication systems, and machine learning models to operate safely and efficiently. Anomalies caused by cyberattacks, like FDI attacks, can potentially cause hazardous behaviors, compromised vehicle control, or erroneous decision-making. Here is a description of an anomaly detection framework to combat FDI attacks on autonomous cars. We discuss the strength, limitations and highlight the gaps in research along with future improvements as well. While doing so we contribute to a complete understanding on FDI attacks. This work aims to fortify resilience against adverse threats and promotes safety in intelligent transportation globally.