Deep learning is a part of the broader family of Machine Learning. It refers to learning multiple levels of representation and abstraction that helps to understand data such as images, sound and text. This paper aims at giving an overview of deep learning, its applications and an approach for Network Intrusion Detection. KDDCup dataset is used for Intrusion detection and a comparison of different deep learning techniques applied for Intrusion Detection is made. A special focus is given on Self taught learning using Sparse Coding and its usage in classification. Self taught learning (STL) is a machine learning framework for using unlabeled data in supervised classification tasks. It is a deep learning approach that comprises of two stages for the classification task. Initially, a good feature representation is learnt from a large collection of unlabeled data, called as Unsupervised Feature Learning (UFL). Finally, the learnt representation is applied to labeled data and then classification task is performed.

Network Intrusion Detection, Classification, Deep Learning, Self-Taught Learning

[1]. Adebayo O. Adetunmbi, Samuel O. Falaki (2008). “Network Intrusion Detection based on Rough Set and k-Nearest Neighbour”, International Journal of Computing and ICT Research, Vol.2, No.1, pp.60-66., http://www.ijcir.org/volume1number2/article7.pdf.
[2]. Bhatnagar and Vishal. (2014). “Data Mining and Analysis in the Engineering Field”, IGI Global.
[3]. Brian Lee, Sandhya Amaresh, Clifford Green, Daniel. (2018). “Comparative Study of Deep Learning Models for Network Intrusion Detection”, SMU Data Science Review”, Vol.1, No.1.
[4]. Breiman, L. (2001). “Random Forests”, Machine Learning, Vol.45, Issue 1, pp.5-32.
[5]. Dietterich, T.G. (2000). “An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization”, Machine Learning, Vol.40, Issue 2, pp.139–157.
[6]. Ho, T.K. (1998). “The Random Subspace method for constructing decision forests”, IEEE transaction on Pattern Analysis and Machine Intelligence, Vol.20, Issue 8, pp.832-844.
[7]. KDD CUP DATASET (1999). http://kdd.ics.uci.edu/databases/kddcup99/
[8]. Kok-Chin Khor, et al (2009). “From Feature Selection to Building of Bayesian Classifiers: A Network Intrusion Detection Perspective”, American Journal of Applied Sciences, Vol.6, No.11, pp.1948-1959.
[9]. Lee,W., Stolfo,S.J., and Mok, K.W. (1999). “Algorithms for Mining System Audit Data”, Proceedings of KDD.
[10]. Neveen I.Ghali. (2009). “Feature Selection for Effective Anomaly Based Intrusion Detection”, International Journal of Computer Science and Network Security, Vol.9, No.3, pp.285-289.
[11]. “Understanding Intrusion Detection Systems”, SANS Institute InfoSec Reading Room.
[12]. Quamar Niyaz, Weiqing Sun, Ahmad Y Javaid, Mansoor Alam (2015). “A Deep Learning Approach for Network Intrusion Detection System”, ACM Digital Library, BICT’15, pp.21-26.
[13]. Venkata Lakshmi, S. and Edwin Prabakaran, T. (2014).
“Application of k-Nearest Neighbour Classification Method for Intrusion Detection in Network Data”, International Journal of Computer Applications, (0975-8887) Vol.97, No.7, pp.34-37.
[14]. Venkata Lakshmi, S. and Edwin Prabakaran, T. (2014). “A comparative study of classification of application of classification algorithms on KDDCup dataset to detect intrusions using WEKA tool”, International Journal of Engineering Research and Technology, Conference Proceedings of RACMS, pp.69-71.
[15]. Venkata Lakshmi, S. and Edwin Prabakaran, T. (2015). “Performance Analysis of Multiple Classifiers on KDD Cup dataset using WEKA tool”, Indian Journal of Science and Technology, Vol.8, No.17, pp.1-10.
[16]. Venkata Lakshmi, S. and Edwin Prabakaran, T. (2015). “Deployment of Models developed in Knowledge Flow Process using WEKA tool on KDDCup dataset” presented in the International Conference on Information Technology organized by Thiruthangal Nadar College, Chennai.
[17]. Venkata Lakshmi, S. and Edwin Prabakaran, T. (2015). “Feature selection and classification of network connection data into normal or attack records using WEKA tool”, Proceedings of the International Conference on Recent Trends in Computer Science and Digital Technology, ICCSDT-2015, pp.72-77, at Guru Shree Shanthi Vijay Jain college, Chennai and received the BEST PAPER AWARD.
[18]. Venkata Lakshmi, S. and Edwin Prabakaran, T. (2016). “Feature selection and Identification of Attacks in Network connection records using classifiers in WEKA tool”, Proceedings of the WCC Centenary International Conference on Viable synergies in Mathematical and Natural Science, pp.215-227 at WCC, Chennai.
[19]. Venkata Lakshmi, S. and Edwin Prabakaran, T. (2018). “Application of Ensemble, Voting and Stacking methods for Better Classification of Network Intrusion Detection and Improving the Performance of Random Forest Method by a new method of Feature Selection”, Mathematical Sciences International Research Journal, Vol.7, Spl.Issue 4, pp.6-16.
[20]. Xindong Wu (2008). “Survey Paper, Top 10 algorithms in data mining”, Knowledge Information Systems, Vol.14, pp.1–37.