Abstract
Recently, due to the growing use of the Internet of Things (IoT) and mobile networks, Internet traffic has been rapidly growing. Information security is a serious problem due to a variety of intrusion incidents of the Internet and various types of network attacks. Since most commercial products of network-based intrusion detection systems which are currently used utilise expert-based misuse detection techniques and statistic-based anomalous behaviour detection techniques, these techniques are still too limited to completely detect various types of network attacks. Using the KDD Cup 1999 data set, well-known supervised learning algorithms of many machine learning algorithms to automatically generate knowledge under our proposed and implemented detect system are applied for normal network packets and various anomalous network packets in this paper. Based on such learned knowledge, experiments to determine whether it is normal or abnormal are examined for various packets, and accuracy and processing speed for five selected supervised learning algorithms are compared and analysed. As a result of analysing the accuracy and processing speed of five well - known supervised learning algorithms, SVMWithSGD and Logistic Regression algorithms have been determined to show the most accurate results. With regard to processing speed, Random Forest and Decision Tree algorithms are the fastest algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Apache: Apache Hadoop. http://en.wikipedia.org/wiki/Apache_Hadoop
Bell, J.: Machine Learning. Wiley, Hoboken (2015)
Caruana, R., Niculescu-Mizil, A.: An empirical comparison of supervised learning algorithms. In: Proceedings of the 23rd International Conference on Machine Learning, ICML 2006, pp. 161–168. ACM, New York (2006)
Choi, J.I.: An empirical comparison between logistic regression models and logistic multilevel models. Master’s thesis, Yonsei University (2005)
Frampton, M.: Mastering Apache Spark. Packt Publishing, Birmingham (2015)
Jang, E.J.: Comparison and analysis of several data mining methods to find out meaningful variables according to the type of response variable. Master’s thesis, Ewha Womans University (2013)
Jang, K.Y.: Automatic generation of detection pattern of network attack using the decision tree algorithm. Master’s thesis, Chonnam National University (2004)
Jeong, H.D.J., Ryu, M.U., Ji, M.J., Cho, Y.B., Ye, S.K., Lee, J.S.R.: DDoS attack analysis using the improved ATMSim. J. Internet Comput. Serv. (JICS) 17(2), 19–28 (2016)
Kim, J.H.: Design and implementation of a parallel distributed spatial reasoner using apache spark. Master’s thesis, Kyonggi University (2016)
Kim, S.H.: Transportation bigdata analysis and performance evaluation in apache spark. Master’s thesis, Chungbuk National University (2015)
Kim, S.J., Choe, H.J., Yoon, S.R.: Performance analysis of stochastic gradient descent algorithm in parallel distributed system. In: Proceedings of KIISE, pp. 1542–1544 (2015)
Kwon, T.H.: A performance comparison study on data analysis tools: based on machine learning. Master’s thesis, Soongsil University (2016)
Lee, C.G.: A realtime monitoring and prediction system based on machine learning algorithm. Master’s thesis, Dankook University (2016)
Lee, Y.K.: The comparison between Hadoop MapReduce and Spark Device’s machine learning performance. Master’s thesis, Soongsil University (2015)
Murphy, K.P.: Machine Learning: A Probabilistic Perspective. The MIT Press, Cambridge (2012)
Pentreath, N.: Machine Learning with Spark. Packt Publishing, Birmingham (2015)
Tavallaee, M., Bagheri, E., Lu, W., Ghorbani, A.A.: A detailed analysis of the KDD Cup. 99 data set. In: Proceedings of the IEEE 2009 Symposium on Computational Intelligence for Security and Defense Applications (CISDA 2009), Ontario, Canada, pp. 53–58 (2009)
University of California, Irvine: KDD Cup 1999 (1999). http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html
Acknowledgment
The authors would like to give thanks to the funding agencies for providing financial support. Parts of this work were supported by a research grant from Korean Bible University and Korea Institute of Science and Technology Information. The authors also thank Susan Elizabet Nel and anonymous referees for their constructive remarks and valuable comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Jeong, HD.J. et al. (2018). A Search for Computationally Efficient Supervised Learning Algorithms of Anomalous Traffic. In: Barolli, L., Enokido, T. (eds) Innovative Mobile and Internet Services in Ubiquitous Computing . IMIS 2017. Advances in Intelligent Systems and Computing, vol 612. Springer, Cham. https://doi.org/10.1007/978-3-319-61542-4_58
Download citation
DOI: https://doi.org/10.1007/978-3-319-61542-4_58
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-61541-7
Online ISBN: 978-3-319-61542-4
eBook Packages: EngineeringEngineering (R0)