|
ИСТИНА |
Войти в систему Регистрация |
Интеллектуальная Система Тематического Исследования НАукометрических данных |
||
Continuous Keystroke Dynamics-Based User Authentication Using Modified Hausdorff Distanceстатья
Информация о цитировании статьи получена из
Scopus
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 9 августа 2021 г.
- Авторы: Zhuravskii Maksim, Kazachuk Maria, Petrovskiy Mikhail, Mashechkin Igor
- Журнал: Lecture Notes in Computer Science
- Том: 12680
- Год издания: 2021
- Первая страница: 223
- Последняя страница: 236
- DOI: 10.1007/978-3-030-73216-5_16
- Аннотация: Continuous keystroke dynamics-based user authentication methods are one of the most perspective means of user authentication in computer systems. Such methods do not require specialized equipment and allow detection of user change anytime during a user session. In this paper, we explore new approaches to solving the problem based on Hausdorff distance and its modification, including a new method, the sum of maximum coordinate deviations. We compare proposed methods to existing ones that are based on distance functions defined in feature space, statistical criteria, and neural networks. Based on the experiments, we observe that the proposed method based on the sum of maximum coordinate deviations with k nearest feature vector selection reports the highest accuracy of all reviewed methods.
- Добавил в систему: Казачук Мария Андреевна