A Filter Feature Selection Algorithm Based on Mutual Information for Intrusion Detection
Source abstract
Abstract
For a large number of network attacks, feature selection is used to improve intrusion detection efficiency. A new mutual information algorithm of the redundant penalty between features (RPFMI) algorithm with the ability to select optimal features is proposed in this paper. Three factors are considered in this new algorithm: the redundancy between features, the impact between selected features and classes and the relationship between candidate features and classes. An experiment is conducted using the proposed algorithm for intrusion detection on the KDD Cup 99 intrusion dataset and the Kyoto 2006+ dataset. Compared with other algorithms, the proposed algorithm has a much higher accuracy rate (i.e., 99.772%) on the DOS data and can achieve better performance on remote-to-login (R2L) data and user-to-root (U2R) data. For the Kyoto 2006+ dataset, the proposed algorithm possesses the highest accuracy rate (i.e., 97.749%) among the other algorithms. The experiment results demonstrate that the proposed algorithm is a highly effective feature selection method in the intrusion detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Network Security and Intrusion Detection · Anomaly Detection Techniques and Applications · Artificial Immune Systems Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Engineering Laboratory for Disaster Backup and Recovery, Information Security Center, School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China
Guizhou Provincial Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China
Funding
the National High Technology Research and Development Program of China (863 Program) · National Key Research and Development Program of China
References (48)
Show source-provided references
1. Internet attacks and intrusion detection system: A review of the literature10.1108/OIR-12-2015-0394 ↗
2. Machine Learning and Deep Learning Methods for Cybersecurity10.1109/ACCESS.2018.2836950 ↗
3. Deep Learning-Based Intrusion Detection with Adversaries10.1109/ACCESS.2018.2854599 ↗
4. Karim, I., Vien, Q.T., Le, T.A., and Mapp, G. (2017). A comparative experimental design and performance analysis of Snort-based intrusion detection system in practical computer networks. MDPI Comput., 6.10.3390/computers6010006 ↗
5. Intrusion response systems: Foundations, design, and challenges10.1016/j.jnca.2015.12.006 ↗
6. Intrusion Detection method Based on Deep Learning
7. Feature selection with controlled redundancy in a fuzzy rule based framework10.1109/TFUZZ.2017.2688358 ↗
8. An Improved Intrusion Detection Algorithm Based on GA and SVM10.1109/ACCESS.2018.2810198 ↗
9. Learning Proximity Relations for Feature Selection10.1109/TKDE.2016.2515588 ↗
10. Effective feature extraction via stacked sparse autoencoder to improve intrusion detection system10.1109/ACCESS.2018.2858277 ↗
11. Peng, H.C., Long, F.H., and Ding, C. (2003, January 21–24). Feature selection for high-dimensional data: A fast correlation-based filter solution. Proceedings of the 20th International Conference on Machine Learning, Washington, DC, USA.
12. Metaheuristic approach for an enhanced mRMR filter method for classification using drug response microarray data10.1016/j.eswa.2017.08.026 ↗
13. Wrappers for feature subset selection10.1016/S0004-3702(97)00043-X ↗
14. Hui, K.H., Ooi, C.S., Lim, M.H., Leong, M.S., and Al-Obaidi, S.M. (2017). An improved wrapper-based feature selection method for machinery fault diagnosis. PLoS ONE, 12.10.1371/journal.pone.0189143 ↗
15. Feature Selection for Classification10.3233/IDA-1997-1302 ↗
16. Crack Fault Classification for Planetary Gearbox Based on Feature Selection Technique and K-means Clustering Method10.1186/s10033-018-0202-0 ↗
17. Toward a reliable anomaly-based intrusion detection in real-world environments10.1016/j.comnet.2017.08.013 ↗
18. Statistical pattern recognition: A review10.1109/34.824819 ↗
19. Using mutual information for selecting features in supervised neural net learning10.1109/72.298224 ↗
20. Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy10.1109/TPAMI.2005.159 ↗
21. Input feature selection for classification problems10.1109/72.977291 ↗
22. Novovičová, J., Somol, P., Haindl, M., and Pudil, P. (2007). Conditional Mutual Information Based Feature Selection for Classification Task, Springer.10.1007/978-3-540-76725-1_44 ↗
23. A two-level hybrid approach for intrusion detection10.1016/j.neucom.2016.06.021 ↗
24. A Novel Real-Time DDoS Attack Detection Mechanism Based on MDRA Algorithm in Big Data
25. (2017, December 20). Kdd Cup 99 Intrusion Detection Dataset Task Description. Available online: http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html.
26. Hybrid feature selection using component co-occurrence based feature relevance measurement10.1016/j.eswa.2018.01.041 ↗
27. Toward intrusion detection using belief decision trees for big data10.1007/s10115-017-1034-4 ↗
28. Alert correlation in collaborative intelligent intrusion detection systems-A survey10.1016/j.asoc.2010.12.004 ↗
29. Detection and classification of anomaly intrusion using hierarchy clustering and SVM10.1002/sec.1547 ↗
30. Application of SVM and ANN for intrusion detection10.1016/j.cor.2004.03.019 ↗
31. Improving classification performance of support vector machine by genetically optimising kernel shape and hyper-parameters10.1007/s10489-010-0260-1 ↗
32. Mutual information-based feature selection for intrusion detection systems10.1016/j.jnca.2011.01.002 ↗
33. Building an intrusion detection system using a filter-based feature selection algorithm10.1109/TC.2016.2519914 ↗
34. Conditional Likelihood Maximisation: A Unifying Framework for Information Theoretic Feature Selection
35. Brown, G. (2009, January 16–18). A New Perspective for Information Theoretic Feature Selection. Proceedings of the International Conference on Artificial Intelligence & Statistics, Clearwater Beach, FL, USA.
36. Kumar, S., Sharma, A., and Tsunoda, T. (2017, January 20–22). An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information. Proceedings of the 16th International Conference on Bioinformatics (InCoB)-Bioinformatics, Shenzhen, China.10.1186/s12859-017-1964-6 ↗
37. Hybrid of binary gravitational search algorithm and mutual information for feature selection in intrusion detection systems10.1007/s00500-015-1942-8 ↗
38. Profiling DNS tunneling attacks with PCA and mutual information10.1093/jigpal/jzw056 ↗
39. A multi-step outlier-based anomaly detection approach to network-wide traffic10.1016/j.ins.2016.02.023 ↗
40. Song, J., Takakura, H., Okabe, Y., Eto, M., Inoue, D., and Nakao, K. (2011, January 10). Statistical analysis of honeypot data and building of Kyoto 2006+ dataset for NIDS evaluation. Proceedings of the First Workshop on Building Analysis Datasets and Gathering Experience Returns for Security, Salzburg, Austria.10.1145/1978672.1978676 ↗
41. Machine Learning Based Intrusion Detection Systems for Class Imbalanced Datasets
42. Belhadj-Aissa, N., and Guerroumi, M. (2016, January 16–18). A New Classification Process for Network Anomaly Detection Based on Negative Selection Mechanism. Proceedings of the 9th International Conference on Security, Privacy, and Anonymity in Computation, Communication and Storage (SpaCCS), Zhangjiajie, China.10.1007/978-3-319-49145-5_24 ↗
43. An effective combining classifier approach using tree algorithms for network intrusion detection10.1007/s00521-016-2418-1 ↗
44. Meena, G., and Choudhary, R.R. (2017, January 1–2). A review paper on IDS classification using KDD 99 and NSL KDD dataset in WEKA. Proceedings of the International Conference on Computer, Communications and Electronics (Comptelix), Jaipur, India.10.1109/COMPTELIX.2017.8004032 ↗
45. Double Behavior Characteristics for One-Class Classification Anomaly Detection in Networked Control Systems10.1109/TIFS.2017.2730581 ↗
46. Kushwaha, P., Buckchash, H., and Raman, B. (2017, January 5–8). Anomaly based intrusion detection using filter based feature selection on KDD-CUP 99. Proceedings of the IEEE Region 10 Conference, Penang, Malaysia.10.1109/TENCON.2017.8227975 ↗
47. Duan, S., Levitt, K., Meling, H., Peisert, S., and Zhang, H. (2014, January 6–9). ByzID: Byzantine Fault Tolerance from Intrusion Detection. Proceedings of the IEEE International Symposium on Reliable Distributed Systems, Nara, Japan.10.1109/SRDS.2014.28 ↗
48. Rosas, F., and Chen, K.C. (December, January 29). Social learning against data falsification in sensor networks. Proceedings of the International Conference on Complex Networks and their Applications, Lyon, France.