Date of Award


Document Type


Degree Name

Master of Science (MS)


Computer Science

First Advisor

Dr. Xiaohong Yuan


Cyber-attacks have increased greatly in recent years. Therefore, the identification of various network attacks has been an important research area. An Intrusion Detection System (IDS), can identify an ongoing invasion or an intrusion which has already occurred. Intrusion Detection is a classification problem. It identifies whether the network traffic behavior is normal or anomalous or identifies the attack types. Various approaches have been proposed to improve the accuracy of classifiers for identifying the intrusion types. Recently, deep learning has emerged as a successful approach in IDSs having a high accuracy rate with its distinctive learning mechanism. In this research, Long Short-Term Memory (LSTM) with Recurrent Neural Network (RNN) were implemented for intrusion detection. Genetic Algorithm (GA) was used for feature selection. Then the performance of the IDS is analyzed by calculating the accuracy, recall, precision, f-score and confusion matrix. NSL-KDD dataset-a refined version of KDD Cup 99’ dataset and which is a benchmark dataset for network intrusion, has been used to analyze the performance of the proposed approach. LSTM-RNN was used to classify NSL-KDD datasets into two classes (normal and abnormal), as well as five-classes (Normal, DoS, Probing, U2R and R2L). The proposed approach indicates that applying GA increases the performance of LSTM-RNN by 10% in both binary and 5-class classification. Then finally, the results of the LSTM-RNN for classifying NSL-KDD data were compared with the results using traditional methods including Support Vector Machine (SVM) and Random Forest (RF) for both binary and multiclass classification. Promising results for multiclass classification have been obtained from the proposed model which is much higher than SVM and RF. For binary classification, the performance of LSTM-RNN is similar to RF. LSTM-RNN has obtained higher accuracy than SVM in both binary and multiclass classification.