<?xml version="1.0" encoding="UTF-8"?>
<XML><RECORDS>
<RECORD>
	<REFERENCE_TYPE>3</REFERENCE_TYPE>
	<AUTHORS>
		<AUTHOR>Davide Ariu</AUTHOR>
		<AUTHOR>Giorgio Giacinto</AUTHOR>
	</AUTHORS>
	<YEAR>2011</YEAR>
	<TITLE>A modular architecture for the analysis of  HTTP payloads based on Multiple Classiļ¬ers</TITLE>
	<SECONDARY_TITLE>10th Int. Workshop on Multiple Classifier Systems (MCS 2011), Naples, Italy</SECONDARY_TITLE>
	<DATE>15/06/2011</DATE>
	<KEYWORDS>
		<KEYWORD>ids00</KEYWORD>
		<KEYWORD>mcs00</KEYWORD>
	</KEYWORDS>
	<ABSTRACT>&lt;div align=&quot;justify&quot;&gt;
In this paper we propose an Intrusion Detection System (IDS) for the detection of attacks against a web server. The system analyzes the requests received by a web server, and is based on a two-stages classi&iuml;&not;cation algorithm that heavily relies on the MCS paradigm. In the &iuml;&not;rst stage the structure of the HTTP requests is modeled using several ensembles of Hidden Markov Models. Then, the outputs of these ensembles are combined using a one-class classi&iuml;&not;cation algorithm. We evaluated the system on several datasets of real tra&iuml;&not;c and real attacks. Experimental results, and comparisons with state-of.the.art detection systems show the e&iuml;&not;ectiveness of the proposed approach.&lt;br /&gt;
&lt;/div&gt;
</ABSTRACT>
	<NOTES><div id="__ss_9555334" style="width: 425px">
 <strong style="display: block; margin: 12px 0pt 4px"><a href="http://www.slideshare.net/pragroup/ariu-workshop-on-multiple-classifier-systems-2011" target="_blank" title="Ariu - Workshop on Multiple Classifier Systems - 2011">Ariu - Workshop on Multiple Classifier Systems - 2011</a></strong>  
</div>
</NOTES>
</RECORD>
</RECORDS></XML>