AI-Based Message Spam Classification Framework for Secure Autonomous Vehicles Communication

With the progress in the field of Autonomous Vehicles (AVs), it becomes crucial to maintain the integrity and security of Vehicle-to-Everything (V2X) communications to further secure safe and reliable transportation. 5G networks serve as the base for these Intelligent Transportation Systems (ITS), but the intervention of spam messages threatens both network efficiency and vehicle safety. This paper thus proposes a Machine Learning (ML)-based spam classification framework which is designed especially for 5G-enabled autonomous vehicle communication systems that helps in the filtering of real time malicious and unwanted messages. Multiple ML classifiers, including Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), and Logistic Regression (LR) have been used in order to detect and neutralize spam traffic across V2X networks. SVM performs best, according to the experimental data, with an accuracy of 0.9476. Without losing the low-latency demands of vehicular communication, it detects spam efficiently. This study discusses challenges associated with this. Our architecture minimizes unwanted traffic while guaranteeing smooth processing of genuine messages. Furthermore, In order to ensure a safer and more effective smart transportation system on 5G networks, this study emphasizes the significance of spam detection in protecting AVs.