Optimizing Automotive Cybersecurity with Cost-Sensitive Decision Forest Algorithm in IoV

In the quickly changing world of connected cars, having strong cybersecurity is essential. To protect vehicular networks from cyber threats, this study provides an Embedded Intrusion Detection System (IDS) that has been optimized using the Cost-Sensitive Decision Forest (CSForest) optimization algorithm. To improve data usefulness and model performance, a thorough preprocessing and feature engineering process was carried out using a real vehicular GPS tracking process from ToN-IoT dataset. After evaluating several machine learning algorithms, CSForest received the best results, scoring 100% accuracy along with flawless precision, recall, and F-measure scores. Our results highlight how well the CSForest-based IDS can detect and stop possible cyberattacks in connected cars, which will improve automotive cybersecurity and create a safer driving environment for vehicular communication systems. The study also emphasizes how crucial it is to keep updating IDS models to handle the ever-changing nature of cyberattacks and maintain the dependability and resilience of vehicular communication systems in the future. The discovery has practical consequences as it can improve connected and autonomous car cybersecurity infrastructure substantially, lowering vulnerabilities and guaranteeing a safer transportation ecosystem.