A Aplicação de uma Arquitetura de Máquinas de Comitê na Autenticação de Usuários através da Dinâmica de Digitação

• Mauro Roisenberg UFSC
• Sérgio Roberto de Lima e Silva Filho UFSC

DOI: https://doi.org/10.5753/sbseg.2006.20943

Abstract

This paper describes the application of neural network committee machines to the authentication problem, particularly for the authentication of computer users through the classification of keystroke dynamics patterns. Keystroke dynamics is a biometric characteristic that encompass the features of users when typing the computer keyboard. The proposed methodology also provides continuous authentication. The results and the associated discussion describe a successful application of neural networks committee machines to a difficult, but important, real world task taken from the security area. In addition the techniques described are widely applicable to other complex pattern classification problems.

References

ALEXANDRE, T. J. Biometrics on smartcards: An approach to keyboard behavioral signature. In Second Smart Card Researsh & Advanced Applications Conference, 1996.

ANAGUN, A. S. & CIN, I. A Neural Network based Computer Access Security System for Multiple Users. Computers & Industrial Engineering, Vol. 35, No. 1-2, pp. 351354, 1998.

BERGADANO, F.; GUNETTI, D. & PICARDI C. User authentication through Keystroke Dynamics. ACM Transactions on Information and System Security (TISSEC), Vol. 5, No. 4, pp. 367-397, 2002.

BLEHA, S.; SLIVINSKY, C. & HUSSIEN, B. Computer-Access Security Systems Using Keystroke Dynamics. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No.12, pp. 1217-1222, 1990.

BROWN, M. & ROGERS, S. J. User identification via keystroke characteristics of typed names using neural networks. International Journal of Man-Machine Studies, Vol. 39, No. 6, pp. 999-1014, 1993.

CAPUANO, N.; MASELLA, M.; MIRANDA, S. & SALERNO, S. User authentication with neural networks. Proceedings of the 5th International Conference on Engineering Applications of Neural Networks EANN 99, Warsaw, Poland, 1999.

COLTELL, O.; BADÍA, J.M. & TORRES, G. Biometric Identification System Based in Keyboard Filtering. Proceedings of XXXIII Annual IEEE International Carnahan Conference on Security Technology, IEEE Pub., pp. 203-209, 1999.

GAINES, R.; LISOWSKI, W.; PRESS, S. & SHAPIRO, N. Authentication by keystroke timing: Some preliminary results. Rand Report R-256-NSF. Rand Corporation, Santa Mônica, CA, 1980.

HAYKIN, S. Redes Neurais Princípios e Práticas. Segunda Edição, Porto Alegre, Editora Bookman, 2001, 900 p.

ILONEN, J. Keystroke Dynamics. Disponível em: http://www.it.lut.fi/kurssit/03-04/010970000/seminars/Ilonen.pdf. Acesso em: 24 jul. 2005.

JOYCE, R. & GUPTA G. Identity Authentication Based on Keystroke Latencies. Communications of the ACM, Vol. 33, No. 2, pp. 168 176, 1990.

MONROSE, F.; REITER, M. K. & WETZEL, S. Password Hardening Based on Keystroke Dynamics. Proceedings of the 6th ACM conference on Computer and communications security, 1999.

MONROSE, F. & RUBIN, A. D. Authentication via Keystroke Dynamics. Proceedings of the 4th ACM conference on Computer and communications security, pp. 48-56, 1997.

OBAIDAT, M. S. A verification Methodology for Computer Systems Users. Proceedings of the 1995 ACM symposium on Applied computing, Nashville, Tennessee, United States, pp. 258-262, 1995.

OBAIDAT, M. S. & SADOUN, B. Verification of Computer Users Using Keystroke Dynamics. IEEE Transactions on System, Man and Cybernetics, Vol. 27, No. 2, pp. 261-269, 1997.

PEACOCK, A. Learning User Keystroke Latency Patterns (Preliminary Report). Disponível em: http://pel.cs.byu.edu/alen/personal/CourseWork/cs572/KeystrokePaper/. Acesso em: 24 jul. 2005.