IoT-based blockchain intrusion detection using optimized recurrent neural network

IoT-based blockchain intrusion detection using optimized recurrent neural network

연구 분야: Networking

학회: Multimedia Tools and Applications

In recent years, Intrusion Detection Systems (IDS) monitor the computer network system by collecting and analyzing data or information by identifying the behavior of the user or predicting the attacks by the automatic response. So, in this paper, the Blockchain-based African Buffalo (BbAB) scheme with Recurrent Neural Network (RNN) model is proposed for detecting the intrusion by enhancing security. Furthermore, normal and malware user datasets are collected and trained in the system and the dataset is encrypted using Identity Based Encryption (IBE). The encrypted data are securely stored in the blockchain in the cloud. Hereafter, Recurrent Neural Network (RNN) was employed to detect the intrusion in a cloud environment. African buffalo optimization was used in the RNN prediction phase for continuous monitoring of intrusion. Finally, the performance results of the developed technique are compared with other conventional models in terms of accuracy, precision, recall, F1-score, and detection rate. The outperformance of the designed model attains better accuracy of 99.87% and high recall of 99.92%.it shows the efficiency of the designed model to protect data and security in cloud computing.