Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection Systems
The development of robust anomaly-based network detection systems, which are preferred over static signal-based network intrusion, is vital for cybersecurity. The development of a flexible and dynamic security system is required to tackle the new attacks. Current intrusion detection systems (IDSs) s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/12/10/167 |
| _version_ | 1797552226708750336 |
|---|---|
| author | Niraj Thapa Zhipeng Liu Dukka B. KC Balakrishna Gokaraju Kaushik Roy |
| author_facet | Niraj Thapa Zhipeng Liu Dukka B. KC Balakrishna Gokaraju Kaushik Roy |
| author_sort | Niraj Thapa |
| collection | DOAJ |
| description | The development of robust anomaly-based network detection systems, which are preferred over static signal-based network intrusion, is vital for cybersecurity. The development of a flexible and dynamic security system is required to tackle the new attacks. Current intrusion detection systems (IDSs) suffer to attain both the high detection rate and low false alarm rate. To address this issue, in this paper, we propose an IDS using different machine learning (ML) and deep learning (DL) models. This paper presents a comparative analysis of different ML models and DL models on Coburg intrusion detection datasets (CIDDSs). First, we compare different ML- and DL-based models on the CIDDS dataset. Second, we propose an ensemble model that combines the best ML and DL models to achieve high-performance metrics. Finally, we benchmarked our best models with the CIC-IDS2017 dataset and compared them with state-of-the-art models. While the popular IDS datasets like KDD99 and NSL-KDD fail to represent the recent attacks and suffer from network biases, CIDDS, used in this research, encompasses labeled flow-based data in a simulated office environment with both updated attacks and normal usage. Furthermore, both accuracy and interpretability must be considered while implementing AI models. Both ML and DL models achieved an accuracy of 99% on the CIDDS dataset with a high detection rate, low false alarm rate, and relatively low training costs. Feature importance was also studied using the Classification and regression tree (CART) model. Our models performed well in 10-fold cross-validation and independent testing. CART and convolutional neural network (CNN) with embedding achieved slightly better performance on the CIC-IDS2017 dataset compared to previous models. Together, these results suggest that both ML and DL methods are robust and complementary techniques as an effective network intrusion detection system. |
| first_indexed | 2024-03-10T15:56:56Z |
| format | Article |
| id | doaj.art-8a596ab843994220aca104b2dda6e461 |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-03-10T15:56:56Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-8a596ab843994220aca104b2dda6e4612023-11-20T15:35:38ZengMDPI AGFuture Internet1999-59032020-09-01121016710.3390/fi12100167Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection SystemsNiraj Thapa0Zhipeng Liu1Dukka B. KC2Balakrishna Gokaraju3Kaushik Roy4Department of Computational Data Science and Engineering, North Carolina A&T State University, Greensboro, NC 27411, USADepartment of Computer Science, North Carolina A&T State University, Greensboro, NC 27411, USAElectrical Engineering and Computer Science Department, Wichita State University, Wichita, KS 67260, USADepartment of Computational Data Science and Engineering, North Carolina A&T State University, Greensboro, NC 27411, USADepartment of Computer Science, North Carolina A&T State University, Greensboro, NC 27411, USAThe development of robust anomaly-based network detection systems, which are preferred over static signal-based network intrusion, is vital for cybersecurity. The development of a flexible and dynamic security system is required to tackle the new attacks. Current intrusion detection systems (IDSs) suffer to attain both the high detection rate and low false alarm rate. To address this issue, in this paper, we propose an IDS using different machine learning (ML) and deep learning (DL) models. This paper presents a comparative analysis of different ML models and DL models on Coburg intrusion detection datasets (CIDDSs). First, we compare different ML- and DL-based models on the CIDDS dataset. Second, we propose an ensemble model that combines the best ML and DL models to achieve high-performance metrics. Finally, we benchmarked our best models with the CIC-IDS2017 dataset and compared them with state-of-the-art models. While the popular IDS datasets like KDD99 and NSL-KDD fail to represent the recent attacks and suffer from network biases, CIDDS, used in this research, encompasses labeled flow-based data in a simulated office environment with both updated attacks and normal usage. Furthermore, both accuracy and interpretability must be considered while implementing AI models. Both ML and DL models achieved an accuracy of 99% on the CIDDS dataset with a high detection rate, low false alarm rate, and relatively low training costs. Feature importance was also studied using the Classification and regression tree (CART) model. Our models performed well in 10-fold cross-validation and independent testing. CART and convolutional neural network (CNN) with embedding achieved slightly better performance on the CIC-IDS2017 dataset compared to previous models. Together, these results suggest that both ML and DL methods are robust and complementary techniques as an effective network intrusion detection system.https://www.mdpi.com/1999-5903/12/10/167network intrusion detectionCIDDSmachine learningdeep learningKNNCART |
| spellingShingle | Niraj Thapa Zhipeng Liu Dukka B. KC Balakrishna Gokaraju Kaushik Roy Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection Systems Future Internet network intrusion detection CIDDS machine learning deep learning KNN CART |
| title | Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection Systems |
| title_full | Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection Systems |
| title_fullStr | Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection Systems |
| title_full_unstemmed | Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection Systems |
| title_short | Comparison of Machine Learning and Deep Learning Models for Network Intrusion Detection Systems |
| title_sort | comparison of machine learning and deep learning models for network intrusion detection systems |
| topic | network intrusion detection CIDDS machine learning deep learning KNN CART |
| url | https://www.mdpi.com/1999-5903/12/10/167 |
| work_keys_str_mv | AT nirajthapa comparisonofmachinelearninganddeeplearningmodelsfornetworkintrusiondetectionsystems AT zhipengliu comparisonofmachinelearninganddeeplearningmodelsfornetworkintrusiondetectionsystems AT dukkabkc comparisonofmachinelearninganddeeplearningmodelsfornetworkintrusiondetectionsystems AT balakrishnagokaraju comparisonofmachinelearninganddeeplearningmodelsfornetworkintrusiondetectionsystems AT kaushikroy comparisonofmachinelearninganddeeplearningmodelsfornetworkintrusiondetectionsystems |