Купить СНПЧ А7 Архангельск, оперативня доставка

crosscheckdeposited

Treinamento de Redes Neurais com Algoritmos Imunológicos em Dinâmica da Digitação

DOI: http://dx.doi.org/10.12721/2237-5112.v02n02a03

http://www.rtic.com.br

downloadpdf

Paulo Henrique Pisani1 & Ana Carolina Lorena2

 

Resumo: O ritmo de desenvolvimento da tecnologia é notável e trouxe diversos avanços como, por exemplo, a identidade digital. Entretanto, a identidade digital potencializou o roubo de identidades devido à maior exposição dos dados. Diante deste cenário, sistemas de detecção de intrusões que analisam o comportamento do usuário mostram-se como uma alternativa promissora para combater este problema. Estes sistemas criam um modelo de comportamento do usuário e, posteriormente, eventos observados que desviem deste modelo são classificados como intrusões em potencial. A dinâmica da digitação, discutida neste artigo, é uma das características que podem ser analisadas para definição do modelo do usuário. Neste trabalho, é feita uma comparação entre o tradicional algoritmo de treinamento de redes neurais backpropagation e duas abordagens evolutivas baseadas em algoritmos imunológicos, atuando no reconhecimento de usuários por dinâmica da digitação.

Palavras-chave: Dinâmica da digitação, redes neurais, algoritmos imunológicos

 

1 Universidade Federal do ABC (UFABC), Santo André, SP. E-mail: paulo.pisani@ufabc.edu.br

2 Universidade Federal de São Paulo (UNIFESP), São José dos Campos, SP. E-mail: aclorena@unifesp.br

 

Literatura Citada

[1] L. Wang and X. Geng, Behavioral Biometrics for Human Identification, ser. Medical Information Science Reference. IGI Global, 2009. doi

[2] M. Karnan, M. Akila, and N. Krishnaraj, “Biometric personal authentication using keystroke dynamics: A review,” Applied Soft Computing, vol. 11, pp. 1565–1573, 2011. doi

[3] J. Timmis, A. Hone, T. Stibor, and E. Clark, “Theoretical advances in artificial immune systems,” Theoretical Computer Science, vol. 403, pp. 11–32, 2008. doi

[4] L. N. de Castro, Fundamentals of Natural Computing. Chapman & Hall/CRC, 2006. 

[5] P. Pisani and A. Lorena, “Evolutionary neural networks applied to keystroke dynamics: Genetic and immune based,” in Evolutionary Computation (CEC), 2012 IEEE Congress on, june 2012, pp. 2965–2972. doi

[6] D. Hosseinzadeh and S. Krishnan, “Gaussian mixture modeling of keystroke patterns for biometric applications,” Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 38, no. 6, pp. 816–826, 2008. doi

[7] A. Peacock, X. Ke, and M. Wilkerson, “Typing patterns: a key to user identification,” Security Privacy, IEEE, vol. 2, no. 5, pp. 40–47, 2004. doi

[8] R. Moskovitch, C. Feher, A. Messerman, N. Kirschnick, T. Mustafic, A. Camtepe, B. Lohlein, U. Heister, S. Moller, L. Rokach, and Y. Elovici, “Identity theft, computers and behavioral biometrics,” in Intelligence and Security Informatics, 2009. ISI ’09. IEEE International Conference on. IEEE, 2009, pp. 155–160. doi

[9] P. H. Pisani and S. do Lago Pereira, “Lamarckian evolution of neural networks applied to keystroke dynamics,” in ICEC 2010 - Proceedings of the International Conference on Evolutionary Computation, [part of the International Joint Conference on Computational Intelligence IJCCI 2010], Valencia, Spain, October 24 - 26, 2010, J. Filipe and J. Kacprzyk, Eds. SciTePress, 2010, pp. 358–364. 

[10] H. Crawford, “Keystroke dynamics: Characteristics and opportunities,” in Privacy Security and Trust (PST), 2010 Eighth Annual International Conference on, 2010, pp. 205–212. doi

[11] R. Gaines, W. Lisowski, S. Press, and N. Shapiro, “Authentication by keystroke timing: some preliminary results, technical report,” Rand Corporation, Tech. Rep., 1980. 

[12] P. H. Pisani and A. C. Lorena, “Detecção de intrusões com dinâmica da digitação: uma revisão sistemática,” Universidade Federal do ABC, Santo André, Brasil, Technical Report 06/2011, dezembro 2011. 

[13] D. Gunetti and C. Picardi, “Keystroke analysis of free text,” ACM Trans. Inf. Syst. Secur., vol. 8, pp. 312–347, 2005. doi

[14] J. Montalvao, C. Almeida, and E. Freire, “Equalization of keystroke timing histograms for improved identification performance,” in Telecommunications Symposium, 2006 International. IEEE, 2006, pp. 560–565. doi

[15] R. Giot, M. El-Abed, and C. Rosenberger, “Keystroke dynamics with low constraints SVM based passphrase enrollment,” in Biometrics: Theory, Applications, and Systems, 2009. BTAS 2009. IEEE 3rd International Conference on. IEEE, 2009, pp. 1–6. doi

[16] K. Killourhy and R. Maxion, “The effect of clock resolution on keystroke dynamics,” in Recent Advances in Intrusion Detection, ser. Lecture Notes in Computer Science, R. Lippmann, E. Kirda, and A. Trachtenberg, Eds. Springer Berlin / Heidelberg, 2008, vol. 5230, pp. 331–350. 

[17] R. Rodrigues, G. Yared, C. do N. Costa, J. Yabu-Uti, F. Violaro, and L. Ling, “Biometric access control through numerical keyboards based on keystroke dynamics,” in Advances in Biometrics, ser. Lecture Notes in Computer Science, D. Zhang and A. Jain, Eds. Springer Berlin / Heidelberg, 2005, vol. 3832, pp. 640–646. 

[18] S. Bleha, C. Slivinsky, and B. Hussien, “Computer-access security systems using keystroke dynamics,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 12, no. 12, pp. 1217–1222, 1990. doi

[19] J. R. M. Filho and E. O. Freire, “On the equalization of keystroke timing histograms,” Pattern Recognition Letters, vol. 27, no. 13, pp. 1440–1446, 2006. doi

[20] K. Killourhy and R. Maxion, “Why did my detector do that?! predicting keystroke-dynamics error rates,” in Recent Advances in Intrusion Detection, ser. Lecture Notes in Computer Science, S. Jha, R. Sommer, and C. Kreibich, Eds. Springer Berlin / Heidelberg, 2010, vol. 6307, pp. 256–276. 

[21] N. Bartlow and B. Cukic, “Evaluating the reliability of credential hardening through keystroke dynamics,” in Software Reliability Engineering, 2006. ISSRE ’06. 17th International Symposium on. IEEE, 2006, pp. 117–126. doi

[22] W. Chang, “Reliable keystroke biometric system based on a small number of keystroke samples,” in Emerging Trends in Information and Communication Security, ser. Lecture Notes in Computer Science, G. Muller, Ed. Springer Berlin / Heidelberg, 2006, vol. 3995, pp. 312–320. 

[23] E. Yu and S. Cho, “Novelty detection approach for keystroke dynamics identity verification,” in Intelligent Data Engineering and Automated Learning, ser. Lecture Notes in Computer Science, J. Liu, Y.-m. Cheung, and H. Yin, Eds. Springer Berlin / Heidelberg, 2003, vol. 2690, pp. 1016–1023. 

[24] S. Haykin, Redes Neurais: Princípios e Prática, 2a Edição. Bookman, 1999. 

[25] K. W. C. Ku, M. W. Mak, and W. C. Siu, Approaches to combining local and evolutionary search for training neural networks: a review and some new results. Springer-Verlag New York, Inc., 2003, pp. 615–641. 

[26] X. Yao, “Evolving artificial neural networks,” Proceedings of the IEEE, vol. 87, no. 9, pp. 1423–1447, sep 1999. doi

[27] P. A. C. Valdivieso, M. G. Arenas, F. J. G. Castellano, J. J. M. Guervos, A. Prieto, V. M. Rivas, and G. Romero, “Lamarckian evolution and the baldwin effect in evolutionary neural networks,” CoRR, 2006. 

[28] J. Yang, M. Gong, L. Jiao, and L. Zhang, “Improved clonal selection algorithm based on lamarckian local search technique,” in Evolutionary Computation, 2008. CEC 2008. (IEEE World Congress on Computational Intelligence). IEEE Congress on, 2008, pp. 535–541. doi

[29] J. F. Kolen, J. B. Pollack, J. F. Kolen, and J. B. Pollack, “Back propagation is sensitive to initial conditions,” in Complex Systems. Morgan Kaufmann, 1990, pp. 860–867.