The consideration of information security is important in providing the safety and integrity of sophisticated car systems. Automated Emergency Braking (AEB) system is one of the important elements in improving the safety of a vehicle by averting collisions. There are however challenges in the existing AEB systems also because of the sensor limitations, environmental factors as well as real-time response constraints. The current paper describes a predictive control algorithm, created as a result of machine learning, which will be used to enhance the work of the AEB system. The algorithm implements the synergistic data of radar, LiDAR and cameras in order to promote the achieveability of decreased collision predictions and timely braking. In attempts to meet the security vulnerability, the proposed system incorporates information security measures in order to shield sensor data and communication channels by cyber threats. Simulations done in a framework of MATLAB reflect the enhanced validity and responsiveness of the braking decisions over conventional AEB systems. The most important key performance indicators, including the collision avoidance rate and braking efficiency, are introduced to prove the effectiveness of the offered system. The results show that machine learning, multi-sensor fusion, and information security may be combined to promote the safety of autonomous vehicles and protect against security risks.