Intrusion Detection System using Intelligent Deep Boltzmann Machine

Abstract

In the wireless communication identifying the attacks and ensuring the data/information security is the primary role played by the Intrusion Detection System. In an uncompromised network the network traffic monitored at these two different points in the network should be identical. If differences are detected in the data transmission this may indicate an intrusion of the computer network. The IDS System performs the vital role for the security of the network, consist of three main components: data collection, feature selection/conversion and decision engine. Data preprocessing provides high-quality data for subsequent processing, then different type of feature is extracted from the processed data as vector. The performance is evaluated using the network analysis metrics such as key generation delay, key sharing delay and the hash code generation time for both MLSDN and the proposed Deep Learning (DLSDN). The evaluation shows that the proposed system achieves the better performance in the credential generation processing and in the malicious nodes validation.