Effective Intrusion Detection Model Using Raptor Optimized Deep Convolutional Neural Network
Kshyamasagar Mahanta, Hima Bindu Maringanti, Pradeepkumar Bhale · 2023
Malicious behavior in the system must be recognized for ensure security because the occurrence of the intrusions can threaten the valuable data and threatens the quality of the network. An important area of research in network security is network intrusion detection. In recent years the intrusion detection model faced several problems due to low accuracy, data imbalance, lack of optimization and so on. To overcome this issue, in this research, a raptor-optimized deep CNN is used to develop the intrusion detection model, where the occurrence of intrusions is effectively detected. The deep CNN classifier effectively learns the features, and the enabling of the raptor optimization optimizes the weights and bias parameters to enhance the performance of the deep CNN classifier. The raptor optimization improves the classifier convergence time and global search capability, and the enabling of Synthetic Minority Oversampling Technique (SMOTE) resolved the issues of data imbalance, which reduced the complexity of the system. By evaluating the parameters of accuracy, sensitivity, and specificity, the research's superiority is demonstrated, and the suggested raptor-optimized deep CNN classifier achieved values of 96.51%, 90.23%, and 97.71% for dataset 1. The proposed raptor optimization also achieved values of 95.39%, 95.83%, and 95.15% for dataset 2, which is highly efficient compared to other existing methods.