DETECTION FUNCTIONALITY OF INTERNAL THREATS BASED ON MOUSE DY-NAMICS
Keywords:
insider threat detection, identity authentication, convolutional neural networks, GoogLeNet network, mouse behavior analysis, basic mouse operations, fake authentication, experiment, accuracyAbstract
Abstract. This study explores the problem of detecting insider threats through identity authentication using GoogLeNet network and mouse operation-generated data. We propose a method based on convolutional neural networks and mouse behavior analysis for effective detection of insider threats and fake authentication. We conducted experiments on various datasets with different numbers of basic mouse operations. The results showed that the proposed method achieves high accuracy in detecting insider threats. Our research confirms the potential of using GoogLeNet network and mouse operation analysis in the task of detecting insider threats and provides a basis for further research in this field.
References
Antal M., Buza K., Fejer N. SapiAgent: A Bot Based on Deep Learning to Generate Human-Like Mouse Trajectories //IEEE Access. – 2021. – Т. 9. – С. 124396-124408.
Ciaramella G. et al. Continuous and Silent User Authentication Through Mouse Dynamics and Explainable Deep Learning //2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA). – IEEE, 2022. – С. 1791-1798.
Enström O. Authentication Using Deep Learning on User Generated Mouse Movement Images. – 2019.
Kingma D. P., Ba J. Adam: A method for stochastic optimization //arXiv preprint arXiv:1412.6980. – 2014.
McCann M. T., Jin K. H., Unser M. Convolutional neural networks for inverse problems in imaging: A review //IEEE Signal Processing Magazine. – 2017. – Т. 34. – №. 6. – С. 85-95.
N.A. Hamid, S. Safei, S.D.M. Satar, S. Chuprat, R. Ahmad (201 l). Mouse movement behavioral biometric systems. Proceedings of the International Conference on User Science and Engineering (i-USEr), Selangor, Malaysia, 29 November-l December 20ll, pp. 206-2ll.
Wei A., Zhao Y., Cai Z. A deep learning approach to web bot detection using mouse behavioral biometrics //Biometric Recognition: 14th Chinese Conference, CCBR 2019, Zhuzhou, China, October 12–13, 2019, Proceedings 14. – Springer International Publishing, 2019. – С. 388-395.
Y.X.M. Tan, A. Iacovazzi, I. Homoliak, Y. Elovici, A. Binder (20l9). Adversarial attacks on remote user authentication using behavioural mouse dynamics. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, l4-l9 July 20l9, pp. l-l0.
Yuan S., Wu X. Deep learning for insider threat detection: Review, challenges and opportunities //Computers & Security. – 2021. – Т. 104. – С. 102221.
Zhou Y. T. et al. Image restoration using a neural network //IEEE transactions on acoustics, speech, and signal processing. – 1988. – Т. 36. – №. 7. – С. 1141-1151.
Есипов Д.А., Асланова Н., Шабала Е.Е., Щетинин Д.С., Попов И.Ю. МЕТОД ОБНАРУЖЕНИЯ ИНЦИДЕНТОВ ИНФОРМАЦИОННОЙ БЕЗОПАСНОСТИ ПО АНОМАЛИЯМ В БИОМЕТРИЧЕСКИХ ПОВЕДЕНЧЕСКИХ ЧЕРТАХ ПОЛЬЗОВАТЕЛЯ // Научно-технический вестник информационных технологий, механики и оптики. 2022. №4.
М. В. Тумбинская, Н. Ф. Асадуллин, Р. Р. Муртазин Моделирование аутентификации пользователей по динамике нажатий клавиш в промышленных автоматизированных системах // Программные продукты и системы. 2020. №2. URL:
Маҳкамов Анваржон Абдужабборович, Инадуллаев Холбек Ўрал Ўғли СРАВНИТЕЛЬНЫЙ АНАЛИЗ БИОМЕТРИЧЕСКИХ СИСТЕМ В ОБЕСПЕЧЕНИИ ИНФОРМАЦИОННОЙ БЕЗОПАСНОСТИ // Universum: технические науки. 2021. №12-1 (93).
Мельников Георг Андреевич, Карпук Анатолий Алексеевич ОБНАРУЖЕНИЕ ПОПЫТОК НЕСАНКЦИОНИРОВАННОГО ДОСТУПА НА ОСНОВЕ ВЫЯВЛЕНИЯ НЕСТАНДАРТНЫХ ПОВЕДЕНЧЕСКИХ ФАКТОРОВ // Universum: технические науки. 2021. №3-1 (84). URL:
Уймин А.Г., Морозов И.М. СРАВНИТЕЛЬНЫЙ АНАЛИЗ ИНСТРУМЕНТОВ НЕПРЕРЫВНОЙ ОНЛАЙН-АУТЕНТИФИКАЦИИ И СИСТЕМ ОБНАРУЖЕНИЯ АНОМАЛИЙ ДЛЯ ПОСТОЯННОГО ПОДТВЕРЖДЕНИЯ ЛИЧНОСТИ ПОЛЬЗОВАТЕЛЯ // T-Comm. 2022. №5.
