Keystroke Dynamics Aplicado a la Clasificación de Intrusos
Abstract
La dinámica de tipeo ha demostrado ser una técnica biométrica de comportamiento eficiente como parte de las
técnicas de detección de intrusos. En este trabajo se busca elaborar algoritmos para clasificar intrusos por medio del
análisis de sus patrones de tipeo a la hora de realizar acciones dentro de un servidor. Para la selección de
características de los patrones se recurrió a algoritmos evolutivos utilizando los enfoques de filtrado (filter) y de
envoltorio (wrapper). Se cuenta con datos provenientes de la captura de teclas presionadas por intrusos reales en
diversos honeypots. Las principales características de este estudio consisten en la caracterización y reconocimiento
de intrusos reales y no de usuarios, considerándose la detección de las personas y no las acciones. Se muestran los
resultados obtenidos para la clasificación experimentando con redes autoorganizadas basadas en la Teoría de la
Resonancia Adaptativa (ART) y mapas autoorganizados de Kohonen (SOM), y el método estadístico kmeans.
Se
obtuvo un modelo que se desempeñó satisfactoriamente.
Downloads
References
Araújo L. C. F., Lizárraga M. G., et al. (2005). "Autentificación personal por dinámica de tecleo basada en lógica difusa." IEEE
COMPUTER SOCIETY.
Azevedo G.L.F. , Cavalcanti G.D.C. , et al. (2007). "An approach to feature selection for keystroke dynamics systems based on PSO
and feature weighting." IEEE COMPUTER SOCIETY.
Bergadano Francesco, Gunetti Daniele, et al. (2002). "User Authentication through Keystroke Dynamics." ACM.
Brio Bonifacio Martín del y Molina Alfredo Sanz (2001). Redes Neuronales y Sistemas Difusos. Bogotá, Colombia, Alfaomega Grupo
Editor.
ChengHuang
Jiang, Shiuhpyng Shieh, et al. (2007). Keystroke statistical learning model for web authentication. Proceedings of the
nd ACM symposium on Information, computer and communications security. Singapore, ACM.
Cho TaiHoon
(2006). "Pattern Classification Methods for Keystroke Analysis." SICEICASE
International Joint Conference.
Duda Richard O., Hart Peter E., et al. (2001). Pattern Classification, Wiler InterScience.
Dy Jennifer G. y Brodley Carla E. (2004). "Feature Selection for Unsupervised Learning." J. Mach. Learn. Res. 5: 845889.
Escudero Laureano F. (1977). Reconocimiento de Patrones. Madrid, España, Paraninfo.
Gunetti Daniele y Picardi Claudia (2005). "Keystroke Analysis of Free Text." ACM.
Guyon Isabelle (2003). "An introduction to variable and feature selection." J. Mach. Learn. Res. 3: 11571182.
Hilera José R. y Martínez Víctor J. (1995). Redes Neuronales Artificiales. Fundamentos, modelos y aplicaciones. Madrid, España, Rama.
Kacholia Varun y Pandit Shashank (2004). "Biometric Authentication using Random Distributions (BioART)." shashankpandit.com.
Lee Cheng JaeWook,
Choi SungSoon,
et al. (2007). "An Evolutionary Keystroke Authentication Based on Ellipsoidal Hypothesis
Space." ACM.
Mroczkowski Piotr (2004). "Identity Verification using Keyboard Statistics." Linkoping University, Electronic Press.
Obaidat M. S. y Sadoun Balqies (1997). "Verification of Computer Users Using Keystroke Dynamics.":IEEE COMPUTER
SOCIETY.
Paeckock Alen, Ke Xian, et al. (2004). "Typing Patterns: A Key to User Identification." IEEE COMPUTER SOCIETY.
Rhee F.C.H.
y Lee Young Je (1999). "Unsupervised feature selection using a fuzzygenetic
algorithm." IEEE COMPUTER
SOCIETY.
Robinson John, Liang Vicky, et al. (1998). "Computer user verification using login string Keystroke Dynamics." IEEE COMPUTER
SOCIETY.
Shepherd S J (1995). "Continuous Authentication by analysis of keyboard typing characteristics." IEEE COMPUTER SOCIETY.
Sim Terence y Janakiraman Rajkumar (2007). "Are Digraphs Good for FreeText
Keystroke Dynamics?" IEEE COMPUTER
SOCIETY.
SondbergMadsen
Nicolaj, Thomsen Casper, et al. (2003). "Unsupervised feature subset selection." ECML/PKDD.
Sung KiSeok
y Cho Sungzoon (2006). "GA SVM wrapper ensemble for keystroke dynamics authentication." Lecture notes in
computer science.
Villani Mary, Tappert Charles, et al. (2006). "Keystroke Biometric Recognition Studies on LongText
Input under Ideal and
ApplicationOriented
Conditions." SCIS.
Yijuan Lu, Ira Cohen, et al. (2007). Feature selection using principal feature analysis. Proceedings of the 15th international conference
on Multimedia. Augsburg, Germany, ACM.
YongSeog Kim, Street W. Nick, et al. (2000). Feature selection in unsupervised learning via evolutionary search. Proceedings of the
sixth ACM SIGKDD international conference on Knowledge discovery and data mining. Boston, Massachusetts, United States, ACM.
YongSeog Kim, Street W. Nick, et al. (2003). Feature selection in data mining. Data mining: opportunities and challenges, IGI
Publishing: 80105.
Yu Enzhe y Cho Sungzoon (2003). "Biometricsbased
Password Identity Verification: Some Practical Issues and Solutions."
Yu Enzhe y Cho Sungzoon (2004). "Keystroke dynamics identity verification—its problems and practical solutions." Elsevier Ltd.
Zheng Zhao y Huan Liu (2007). Spectral feature selection for supervised and unsupervised learning. Proceedings of the 24th
international conference on Machine learning. Corvalis, Oregon, ACM.
Zhu Zexuan, Ong YewSoon,
et al. (2007). "Wrapperfilter
feature selection algorithm using a memetic framework." IEEE
COMPUTER SOCIETY.
The articles published in the journal Ciencia y Tecnología are the exclusive property of their authors. Their opinions and content belong to their authors, and the Universidad de Palermo declines all responsibility for the rights that may arise from reading and/or interpreting the content of the published articles.
The reproduction, use or exploitation by any third party of the published articles is not authorized. Its use is only authorized for exclusively academic and/or research purposes.
