Anomaly-Based Intrusion Detection System in WSN using DNN Algorithm

Abstract

Intrusion detection systems (IDSs) are a necessary principle in WSN security, which can successfully prevent various hackers' and intruders' attempts to hack the network. In this research, we address the problem of achieving high accuracy in detecting intrusions in WSNs due to specific characteristics of WSN data, including the appropriate dataset, the drawbacks of feature selection, and choosing the proper algorithms for the classification process. In this paper, we proposed the anomaly-based IDS model using the DNN algorithm and mutual information (MI) technology to select features. The proposed model has been implemented using the Python language used in the Anaconda platform and relying on the standard NSL-KDD dataset. The experimental results showed the capability of the proposed model to achieve high-performance accuracy in intrusion detection using the DNN algorithm compared to the state-of-the-art. The proposed model outperforms other previous relevant works by 3.65% enhancement in terms of accuracy.