Ensemble-By-Session Method on Keystroke Dynamics based User Authentication

다국어 초록 (Multilingual Abstract)

There are many free applications that need users to sign up before they can use the applications nowadays. It is difficult to choose a suitable password for your account. If the password is too complicated, then it is hard to remember it. However, it is easy to be intruded by other users if we use a very simple password. Therefore, biometric-based approach is one of the solutions to solve the issue. The biometric-based approach includes keystroke dynamics on keyboard, mice, or mobile devices, gait analysis and many more. The approach can integrate with any appropriate machine learning algorithm to learn a user typing behavior for authentication system. Preprocessing phase is one the important role to increase the performance of the algorithm. In this paper, we have proposed ensemble-by-session (EBS) method which to operate the preprocessing phase before the training phase. EBS distributes the dataset into multiple sub-datasets based on the session. In other words, we split the dataset into session by session instead of assemble them all into one dataset. If a session is considered as one day, then the sub-dataset has all the information on the particular day. Each sub- dataset will have different information for different day. The sub-datasets are then trained by a machine learning algorithm. From the experimental result, we have shown the improvement of the performance for each base algorithm after the preprocessing phase.

목차 (Table of Contents)

• Abstract
• 1. Introduction
• 2. Ensemble-By-Session Method
• 2.1 Distribution of sub-dataset
• 2.2 Training phase and testing phase
• 3. Dataset
• 3.1 CMU benchmark dataset
• 3.2 Performance criteria using ROC curves
• 4. Experimental Result
• 5. Related work
• 6. Conclusion
• Acknowledgement
• References

참고문헌 (Reference)

1 S. Cho, "Web-based keystroke dynamics identity verification using neural network" 10 (10): 295-307, 2000

2 R. Giot, "Web-based benchmark for keystroke dynamics biometric systems: A statistical analysis" 11-15, 2012

3 X. Wang, "User authentication via keystroke dynamics based on difference subspace and slope correlation degree" 22 (22): 707-712, 2012

4 T. G. Dietterich, "Multiple classifier systems" Springer 1-15, 2000

5 Z. Syed, "Leveraging variations in event sequences in keystroke-dynamics authentication systems" 9-16, 2014

6 E. Yu, "Keystroke dynamics identity verification - its problems and practical solutions" 23 (23): 428-440, 2004

7 S. Z. S. Idrus, "Image analysis and recognition" Springer 11-18, 2013

8 R. Moskovitch, "Identity theft, computers and behavioral biometrics" 155-160, 2009

9 A. N. H. Nahin, "Identifying emotion by keystroke dynamics and text pattern analysis" 33 (33): 987-996, 2014

10 J. Montalv˜ao, "Contributions to empirical analysis of keystroke dynamics in passwords" 52 : 80-86, 2015

11 K. S. Killourhy, "Comparing anomaly-detection algorithms for keystroke dynamics" 125-134, 2009

12 M. M. Al-Jarrah, "An anomaly detector for keystroke dynamics based on medians vector proximity" 3 (3): 988-993, 2012

13 R. Giot, "A new soft biometric approach for keystroke dynamics based on gender recognition" 11 (11): 35-49, 2012

14 Kenneth Revett, "A Bioinformatics Based Approach to User Authentication via Keystroke Dynamics" 제어·로봇·시스템학회 7 (7): 7-15, 2009