Machine Learning-Based Adaptive Genetic Algorithm for Android Malware Detection in Auto-Driving Vehicles

The growing trend toward vehicles being connected to various unidentified devices, such as other or infrastructure, increases the possibility of external attacks on“vehicle cybersecurity (VC). Detection intrusion is a very important part network security for vehicles, that have open connectivity, and self-driving vehicles. Consequently, has become an requirement in trying protect these attackers more sophisticated using malware can penetrate harm vehicle control units technology advances. Thus, ensuring are safe growth automotive industry people faith it. In this study, machine learning-based detection approach hybrid analysis-based particle swarm optimization (PSO) adaptive genetic algorithm (AGA) presented Android auto-driving “CCCS-CIC-AndMal-2020” dataset containing 13 different categories 9504 features was used experiments. proposed approach, firstly, feature selection performed by applying PSO dataset. next step, performance XGBoost random forest (RF) learning classifiers optimized AGA. experiments performed, 99.82% accuracy F-score were obtained with classifier, which developed PSO-based AGA-based hyperparameter optimization. With 98.72% achieved. Our results show application AGA greatly classification information from analysis.