incluídos papers que han salido del trabajo del máster

Author: unintendedbear

Memoria TFM/Capitulos/06Capitulo6.tex

@@ -50,6 +50,32 @@ \section{Discussion}
 % discuss whether these results are so because of preprocessing or the
 % method... discussion is very important - JJ
 
+%-------------------------------------------------------------------
+\section{Scientific exploitation}
+%-------------------------------------------------------------------
+\label{cap6:sec:papers}
+
+As a result of the work tha has been done, three papers have been accepted (two of them also already presented, and one is to be presented in October 2014) in three conferences.
+
+The paper titled ``\textit{MUSES: A corporate user-centric system which applies computational intelligence methods}'', by A.M. Mora, P. De las Cuevas, and J.J. Merelo, was accepted in a special track session of the \textbf{ACM SAC} conference, celebrated at Gyeongju, Korea, in March 2014. This special session was called \textbf{TRECK}, from \textit{Trust, Reputation, Evidence and other Collaboration Know-how}. The paper was presented at the conference by A.M. Mora.
+
+\begin{description}
+  \item[Abstract] This work presents the description of the architecture of a novel enterprise security system, still in development, which can prevent and deal with the security flaws derived from the users in a company. Thus, the Multiplatform Usable Endpoint Security system (MUSES) considers diverse factors such as the distribution of information, the type of accesses, the context where the users are, the category of users or the mix between personal and private data, among others. This system includes an event correlator and a risk and trust analysis engine to perform the decision process. MUSES follows a set of defined security rules, according to the enterprise security policies, but it is able to self-adapt the decisions and even create new security rules depending on the user behaviour, the specific device, and the situation or context. To this aim MUSES applies machine learning and computational intelligence techniques which can  also be used to predict potential unsafe or dangerous user's behaviour. 
+\end{description}
+
+The paper titled ``\textit{Enforcing Corporate Security Policies via Computational Intelligence Techniques}'', by A.M. Mora, P. De las Cuevas,  J.J. Merelo, S. Zamarripa, and Anna I. Esparcia-Alcázar, was accepted in a worshop at the \textbf{GECCO} conference, celebrated at Vancouver, Canada, in July 2014. This workshop was called \textbf{SecDef} - Workshop on \textit{Genetic and Evolutionary Computation in Defense, Security and Risk Management}. The paper was presented at the conference by J.J. Merelo and Anna I. Esparcia-Alcázar.
+
+\begin{description}
+  \item[Abstract] This paper presents an approach, based in a project in development, which combines Data Mining, Machine Learning and Computational Intelligence techniques, in order to create a user-centric and adaptable corporate security system. Thus, the system, named MUSES, will be able to analyse the user's behaviour (modelled as events) when interacting with the company's server, accessing to corporate assets, for instance. As a result of this analysis, and after the application of the aforementioned techniques, the Corporate Security Policies, and specifically, the Corporate Security Rules will be adapted to deal with new anomalous situations, or to better manage user's behaviour.
+The work reviews the current state of the art in security issues resolution by means of these kind of methods. Then it describes the MUSES features in this respect and compares them with the existing approaches. 
+\end{description}
+
+The third paper derived from this research is titled ``\textit{Going a Step Beyond the Black and White Lists for URL Accesses in the Enterprise by means of Categorical Classifiers}'', by A.M. Mora, P. De las Cuevas, and J.J. Merelo. It was accepted at the \textbf{ECTA} conference, which is going to be held at Rome, Italy, in October 2014.
+
+\begin{description}
+  \item[Abstract] Corporate systems can be secured using an enormous quantity of methods, and the implementation of Black or White lists is among them. With these lists it is possible to restrict (or to allow) the users the execution of applications or the access to certain URLs, among others. This paper is focused on the latter option. It describes the whole processing of a set of data composed by URL sessions performed by the employees of a company; from the preprocessing stage, including labelling and data balancing processes, to the application of several classification algorithms. The aim is to define a method for automatically make a decision of allowing or denying future URL requests, considering a set of corporate security policies. Thus, this work goes a step beyond the usual black and white lists, since they can only control those URLs that are specifically included in them, but not by making decisions based in similarity (through classification techniques), or even in other variables of the session, as it is proposed here. The results show a set of classification methods which get very good classification percentages (95-97\%), and which infer some useful rules based in additional features (rather that just the URL string) related to the user's access. This led us to consider that this kind of tool would be very useful tool for an enterprise. 
+\end{description}
+
 %-------------------------------------------------------------------
 \section{Future Work}
 %-------------------------------------------------------------------

Memoria TFM/otros.bib

@@ -882,6 +882,8 @@ @misc{cpan_json
   lastaccess = {September, 2014}
 }
 
+
+
 %--------------------------------
 % Appendix references
 %--------------------------------