CLSTMNet: A Deep Learning Model for Intrusion Detection

Abstract

Intrusion detection as well distributed denial of service (DDoS) are vital in ensuring computer network security. Some researchers claim that current approaches cannot meet the requirements of today's networks are either not workable or sustainable. In a more specific sense, these concerns are related to an increasing number of human interactions, along with reducing levels of detection ability. With our study, a novel deep learning model for intrusion detection is developed for addressing these issues. We proposed a novel deep learning classification algorithm constructed using Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) named CLSTMNet. Our proposed model has been implemented and evaluated using the benchmark NSL-KDD datasets. Compared with many conventional machine learning algorithms, the satisfied outcomes have been obtained from our model.