Learning User Keystroke Patterns for Authentication
Keystroke authentication is a new access control system
to identify legitimate users via their typing behavior. In this paper,
machine learning techniques are adapted for keystroke authentication.
Seven learning methods are used to build models to differentiate user
keystroke patterns. The selected classification methods are Decision
Tree, Naive Bayesian, Instance Based Learning, Decision Table, One
Rule, Random Tree and K-star. Among these methods, three of them
are studied in more details. The results show that machine learning
is a feasible alternative for keystroke authentication. Compared to
the conventional Nearest Neighbour method in the recent research,
learning methods especially Decision Tree can be more accurate. In
addition, the experiment results reveal that 3-Grams is more accurate
than 2-Grams and 4-Grams for feature extraction. Also, combination
of attributes tend to result higher accuracy.
[1] C. C. Aggarwal. Re-designing distance functions and distance-based
applications for high dimensional data. SIGMOD Rec., 30(1):13-18,
2001.
[2] S. Aha and D. Kibler. Instance based learning algorithms. Machine
Learning, 6:37-66, 1991.
[3] L. C. Arajo, L. H. S. Jr., M. G. Lizrraga, L. L. Ling, and J. B. Yabuuti.
User authentication through typing biometrics features. In First
International Conference on Biometric Authentication, volume 3072,
pages 694-700. Springer, 2004.
[4] Ashbourn and D. M. Julian. Biometrics: Advanced Identity Verification:
The Complete Guide. Springer-Verlag UK, 2000.
[5] F. Bergadano, D. Gunetti, and C. Picardi. User authentication through
keystroke dynamics. ACM Trans. Inf. Syst. Secur., 5(4):367-397, 2002.
[6] S. Bleha, C. Slivinsky, and B. Hussien. Computer-access security
systems using keystroke dynamics. In IEEE Transactions on Pattern
Analysis and Machine Intelligence, volume 12, pages 1217-1222, 1990.
[7] S. Haider, A. Abbas, and A. Zaidi. A multi-technique approach for
user identification through keystroke dynamics. In IEEE International
Conference on Systems, Man and Cybernetics, volume 2, pages 1336-
1341, 2000.
[8] R. C. Holte. Very simple classification rules perform well on most
commonly used datasets. Machine Learning, 11:63-91, 1993.
[9] D. P. Huttenlocher and K. Kedem. Computing the minimum hausdorff
distance for point sets under translation. In Proceedings of the sixth
annual symposium on Computational geometry, pages 340-349. ACM
Press, 1990.
[10] C. G. John and T. E. Leonard. K*: An instance-based learner using
an entropic distance measure. In Proceedings of the 12th International
Conference on Machine Learning, pages 108-114. Morgan Kaufmann,
1995.
[11] G. H. John and P. Langley. Estimating continuous distributions in
bayesian classifiers. In Eleventh Conference on Uncertainty in Artificial
Intelligence, pages 338-345. Morgan Kaufmann Publisher, 1995.
[12] R. Kohavi. The power of decision tables. In Proceedings of the 8th
European Conference on Machine Learning, volume 912 of LNAI, pages
174-189. Springer, 1995.
[13] P. Langley and S. Sage. Tractable average-case analysis of naive
bayesian classifiers. In Eleventh Conference on Uncertainty in Artificial
Intelligence, pages 220-228. Morgan Kaufmann Publisher, 1999.
[14] D.-T. Lin. Computer-access authentication with neural network based
keystroke identity verification. In IEEE Transaction on Neural Networks,
volume 1, pages 174-178, 1997.
[15] U. V. Luxburg and O. Bousquet. Distance-based classification with
lipschitz functions. J. Mach. Learn. Res., 5:669-695, 2004.
[16] T. M. Mitchell. Machine Learning. McGraw-Hill, New York, 1997.
[17] F. Monrose, M. K. Reiter, and S. Wetzel. Password hardening based
on keystroke dynamics. In Proceedings of the 6th ACM conference on
Computer and communications security, volume 6, pages 73-82. ACM
Press, 1999.
[18] F. Monrose and A. Rubin. Authentication via keystroke dynamics. In
Proceedings of the 4th ACM conference on Computer and communications
security, volume 2, pages 48-56. ACM Press, 1997.
[19] M. S. Obaidat. A verification methodology for computer systems users.
In Proceedings of the 1995 ACM symposium on Applied computing,
pages 258-262. ACM Press, 1995.
[20] M. S. Obaidat and B. Sadoun. Verification of computer users using
keystroke dynamics. In IEEE Transaction on Systems, Man and
Cybernetics, part B, volume 27, pages 261-269, 1997.
[21] R. Quinlan. C4.5: Programs for Machine Learning. San Mateo, CA:
Morgan Kaufmann, 1993.
[22] J. Robinson, V. Liang, J. Chambers, and C. MacKenzie. Computer user
verification using login string keystroke dynamics. In IEEE Transaction
on Systems, Man and Cybernetics, Part A, volume 28, pages 236-241,
1998.
[23] D. R. W.G and E. J.H.P. Enhanced password authentication through
fuzzy logic. In IEEE Expert, volume 12, pages 38-45, 1997.
[1] C. C. Aggarwal. Re-designing distance functions and distance-based
applications for high dimensional data. SIGMOD Rec., 30(1):13-18,
2001.
[2] S. Aha and D. Kibler. Instance based learning algorithms. Machine
Learning, 6:37-66, 1991.
[3] L. C. Arajo, L. H. S. Jr., M. G. Lizrraga, L. L. Ling, and J. B. Yabuuti.
User authentication through typing biometrics features. In First
International Conference on Biometric Authentication, volume 3072,
pages 694-700. Springer, 2004.
[4] Ashbourn and D. M. Julian. Biometrics: Advanced Identity Verification:
The Complete Guide. Springer-Verlag UK, 2000.
[5] F. Bergadano, D. Gunetti, and C. Picardi. User authentication through
keystroke dynamics. ACM Trans. Inf. Syst. Secur., 5(4):367-397, 2002.
[6] S. Bleha, C. Slivinsky, and B. Hussien. Computer-access security
systems using keystroke dynamics. In IEEE Transactions on Pattern
Analysis and Machine Intelligence, volume 12, pages 1217-1222, 1990.
[7] S. Haider, A. Abbas, and A. Zaidi. A multi-technique approach for
user identification through keystroke dynamics. In IEEE International
Conference on Systems, Man and Cybernetics, volume 2, pages 1336-
1341, 2000.
[8] R. C. Holte. Very simple classification rules perform well on most
commonly used datasets. Machine Learning, 11:63-91, 1993.
[9] D. P. Huttenlocher and K. Kedem. Computing the minimum hausdorff
distance for point sets under translation. In Proceedings of the sixth
annual symposium on Computational geometry, pages 340-349. ACM
Press, 1990.
[10] C. G. John and T. E. Leonard. K*: An instance-based learner using
an entropic distance measure. In Proceedings of the 12th International
Conference on Machine Learning, pages 108-114. Morgan Kaufmann,
1995.
[11] G. H. John and P. Langley. Estimating continuous distributions in
bayesian classifiers. In Eleventh Conference on Uncertainty in Artificial
Intelligence, pages 338-345. Morgan Kaufmann Publisher, 1995.
[12] R. Kohavi. The power of decision tables. In Proceedings of the 8th
European Conference on Machine Learning, volume 912 of LNAI, pages
174-189. Springer, 1995.
[13] P. Langley and S. Sage. Tractable average-case analysis of naive
bayesian classifiers. In Eleventh Conference on Uncertainty in Artificial
Intelligence, pages 220-228. Morgan Kaufmann Publisher, 1999.
[14] D.-T. Lin. Computer-access authentication with neural network based
keystroke identity verification. In IEEE Transaction on Neural Networks,
volume 1, pages 174-178, 1997.
[15] U. V. Luxburg and O. Bousquet. Distance-based classification with
lipschitz functions. J. Mach. Learn. Res., 5:669-695, 2004.
[16] T. M. Mitchell. Machine Learning. McGraw-Hill, New York, 1997.
[17] F. Monrose, M. K. Reiter, and S. Wetzel. Password hardening based
on keystroke dynamics. In Proceedings of the 6th ACM conference on
Computer and communications security, volume 6, pages 73-82. ACM
Press, 1999.
[18] F. Monrose and A. Rubin. Authentication via keystroke dynamics. In
Proceedings of the 4th ACM conference on Computer and communications
security, volume 2, pages 48-56. ACM Press, 1997.
[19] M. S. Obaidat. A verification methodology for computer systems users.
In Proceedings of the 1995 ACM symposium on Applied computing,
pages 258-262. ACM Press, 1995.
[20] M. S. Obaidat and B. Sadoun. Verification of computer users using
keystroke dynamics. In IEEE Transaction on Systems, Man and
Cybernetics, part B, volume 27, pages 261-269, 1997.
[21] R. Quinlan. C4.5: Programs for Machine Learning. San Mateo, CA:
Morgan Kaufmann, 1993.
[22] J. Robinson, V. Liang, J. Chambers, and C. MacKenzie. Computer user
verification using login string keystroke dynamics. In IEEE Transaction
on Systems, Man and Cybernetics, Part A, volume 28, pages 236-241,
1998.
[23] D. R. W.G and E. J.H.P. Enhanced password authentication through
fuzzy logic. In IEEE Expert, volume 12, pages 38-45, 1997.
@article{"International Journal of Information, Control and Computer Sciences:58955", author = "Ying Zhao", title = "Learning User Keystroke Patterns for Authentication", abstract = "Keystroke authentication is a new access control system
to identify legitimate users via their typing behavior. In this paper,
machine learning techniques are adapted for keystroke authentication.
Seven learning methods are used to build models to differentiate user
keystroke patterns. The selected classification methods are Decision
Tree, Naive Bayesian, Instance Based Learning, Decision Table, One
Rule, Random Tree and K-star. Among these methods, three of them
are studied in more details. The results show that machine learning
is a feasible alternative for keystroke authentication. Compared to
the conventional Nearest Neighbour method in the recent research,
learning methods especially Decision Tree can be more accurate. In
addition, the experiment results reveal that 3-Grams is more accurate
than 2-Grams and 4-Grams for feature extraction. Also, combination
of attributes tend to result higher accuracy.", keywords = "Keystroke Authentication, Pattern recognition, MachineLearning, Instance-based Learning, Bayesian, Decision Tree.", volume = "2", number = "2", pages = "508-6", }
