Neural Network Based Web Log Analysis for Web Intrusion Detection

With the increased attacks of web servers and web applications, it is urgent to develop a system to detect web intrusions. Web log files are stream data recording users’ clicks behavior during surfing the Internet. By carefully analyzing these log files, we can reveal some potential anomalies or attacks so as to reduce the loss of property. A method, that applies neural network method to web intrusion detection based on web server access logs, is proposed in this paper. Before feeding the raw log files into neural network algorithms, we need to preprocess these text files and make sure processed logs are of good quality with less noisy and errors. At the result part, our evaluations also demonstrate that the proposed method is superior to decision tree classifier, which shows neural network method can be transplant to web intrusion detection effectively.

[1]  Debasish Das,et al.  A Web Intrusion Detection Mechanism based on Feature based Data Clustering , 2009, 2009 IEEE International Advance Computing Conference.

[2]  Lai-Cheng Cao.  Detecting Web-Based Attacks by Machine Learning , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[3]  Christopher Krügel,et al.  A multi-model approach to the detection of web-based attacks , 2005, Comput. Networks.

[4]  Mohamed I. Marie,et al.  Web Server Logs Preprocessing for Web Intrusion Detection , 2011, Comput. Inf. Sci..

[5]  Gregory D. Abowd,et al.  The smart floor: a mechanism for natural user identification and tracking , 2000, CHI Extended Abstracts.

[6]  P. Barapatre,et al.  Training MLP neural network to reduce false alerts in IDS , 2008, 2008 International Conference on Computing, Communication and Networking.

[7]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[8]  Yudong Zhang,et al.  Binary PSO with mutation operator for feature selection using decision tree applied to spam detection , 2014, Knowl. Based Syst..

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[11]  Sandeep Kumar,et al.  Classification and detection of computer intrusions , 1996 .

[12]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[13]  Hermann Ney,et al.  LSTM Neural Networks for Language Modeling , 2012, INTERSPEECH.

[14]  D.K. Bhattacharyya,et al.  An intrusion detection mechanism based on feature based data clustering , 2008, 2008 4th International Conference on Emerging Technologies.

[15]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.