Classification Performance Improvement of Keystroke Data

Özbek, Mehmet Erdal

doi:10.1109/asyu48272.2019.8946366

Cited by 2 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [87], Ozbek tried to improve on classification performance of keystroke data by removing the users who degrade the performance. Ozbek used two benchmarking databases with different number of users and passphrases for the evaluation.…”

Section: Impact Of Faulty Users' Datamentioning

confidence: 99%

Keystroke Dynamics: Concepts, Techniques, and Applications

Shadman¹,

Wahab²,

Manno³

et al. 2023

Preprint

View full text Add to dashboard Cite

Reliably identifying and authenticating users remains integral to computer system security. Various novel authentication tenchniques such as biometric authentication systems have been devised in recent years. This paper surveys keystroke-based authentication systems and their applications such as continuous authentication. Keystroke dynamics promises to be non-intrusive and cost-effective as no addition hardware is required other than a keyboard. This survey can be a reference for researchers working on keystroke dynamics.

show abstract

Section: Impact Of Faulty Users' Datamentioning

confidence: 99%

Keystroke Dynamics: Concepts, Techniques, and Applications

Shadman¹,

Wahab²,

Manno³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…First, the behavioural biometrics data, that is, the keystroke data from the databases summarized in Section 3.2 are retrieved. In this paper, we have used 100 users from GREYC data based on the work that offers to discard users having less number of acquisitions [28]. Then the classification performance of each user is obtained from different classifiers provided in Section 3.3 in terms of performance metrics based on the confusion matrix.…”

Section: Proposed Modelmentioning

confidence: 99%

A flexible approach for biometric menagerie on user classification of keystroke data

Özbek

2023

Journal of Electrical Engineering

View full text Add to dashboard Cite

Biometric systems aim to provide reliable authentication and verification of users. The behaviour of the users may alter the authentication performance when accessing these systems. Therefore, clustering users based on their actions is crucial. A biometric menagerie defines and labels user groups statistically according to their variability. However, determining groups is a fuzzy process and it may lead to inconsistencies. In this work, a novel and flexible approach is introduced based on the classification performance of the users data collected in a database without imposing any other restrictions. According to the performance measures obtained from the confusion matrix of the classification algorithms, users are ranked and then clustered. Additionally, the norm of a confusion matrix is offered augmenting the state-of-the-art performance metrics. The proposed scheme is evaluated using the behavioural biometrics modality on two benchmark keystroke databases. The performance results successfully illustrate the alternative way of grouping and identification of users sharing the same behaviour irrespective of the chosen classifiers or performance metrics.

show abstract

Classification Performance Improvement of Keystroke Data

Cited by 2 publications

References 8 publications

Keystroke Dynamics: Concepts, Techniques, and Applications

Keystroke Dynamics: Concepts, Techniques, and Applications

A flexible approach for biometric menagerie on user classification of keystroke data

Contact Info

Product

Resources

About