Dynamic Adaptation Attack Detection Model for a Distributed Multi-Access Edge Computing Smart City

The internet of things (IoT) technology presents an intelligent way to improve our lives and contributes many fields such as industry, communications, agriculture, etc. Unfortunately, IoT networks are exposed attacks that may destroy the entire network consume resources. This paper aims propose process automation auto-configured detection model (IADM) detect prevent malicious traffic behaviors/events at distributed multi-access edge computing in IoT-based smart city. proposed consists two phases. first phase relies on (IPA) technique contains five modules named, specifically, dataset collection pre-processing module, analysis rules action database module. In phase, each module composes connecting give feedback reports about send information next modules. Therefore, any change can be easily detected labeled intrusion. connection (ICM) reduce search time, increase speed, security level. second is dynamic adaptation attack based reinforcement one-shot learning. a multi-classification using Random Forest Trees (RFT), k-Nearest Neighbor (K-NN), J48, AdaBoost, Bagging. learn new changed behaviors reinforced learning zero-day events cities. experiments implemented UNSW-NB 15 dataset. achieves high accuracy rates RFT, K-NN, AdaBoost approximately 98.8%. It noted rate J48 classifier 85.51%, which lower than others. Subsequently, Bagging 98.9% 91.41%, respectively. Additionally, error very low. Similarly, precision, recall, F1-measure depends creating auto-adaptive through small number instances conserve memory device network. false reporting by intrusion system (IDS). devices quickly easily. IADM performance for IDS maintaining consumption, time speed process.