Neural network based method of a user identification by keyboard handwriting
With the development of advanced technologies, the problem of information security is becoming increasingly relevant. Given the development of spyware and digital technology allow more effective attacks on computer systems, including corporate networks, confidentiality can only be achieved through t...
Збережено в:
| Дата: | 2018 |
|---|---|
| Автори: | , , , , |
| Формат: | Стаття |
| Мова: | Ukrainian |
| Опубліковано: |
Інститут проблем реєстрації інформації НАН України
2018
|
| Теми: | |
| Онлайн доступ: | http://drsp.ipri.kiev.ua/article/view/142913 |
| Теги: |
Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|
| Назва журналу: | Data Recording, Storage & Processing |
Репозитарії
Data Recording, Storage & Processing| id |
drspiprikievua-article-142913 |
|---|---|
| record_format |
ojs |
| institution |
Data Recording, Storage & Processing |
| collection |
OJS |
| language |
Ukrainian |
| topic |
information security user authentication neural network keyboard handwriting time functions защита информации идентификация пользователя нейронная сеть клавиатурный почерк временные функции захист інформації ідентифікація користувача нейронна мережа клавіатурний почерк часові функції |
| spellingShingle |
information security user authentication neural network keyboard handwriting time functions защита информации идентификация пользователя нейронная сеть клавиатурный почерк временные функции захист інформації ідентифікація користувача нейронна мережа клавіатурний почерк часові функції Danyliuk, I. I. Karpinets, V. V. Pryimak, A. V. Yaremchuk, Y. E. Kostiuchenko, O. I. Neural network based method of a user identification by keyboard handwriting |
| topic_facet |
information security user authentication neural network keyboard handwriting time functions защита информации идентификация пользователя нейронная сеть клавиатурный почерк временные функции захист інформації ідентифікація користувача нейронна мережа клавіатурний почерк часові функції |
| format |
Article |
| author |
Danyliuk, I. I. Karpinets, V. V. Pryimak, A. V. Yaremchuk, Y. E. Kostiuchenko, O. I. |
| author_facet |
Danyliuk, I. I. Karpinets, V. V. Pryimak, A. V. Yaremchuk, Y. E. Kostiuchenko, O. I. |
| author_sort |
Danyliuk, I. I. |
| title |
Neural network based method of a user identification by keyboard handwriting |
| title_short |
Neural network based method of a user identification by keyboard handwriting |
| title_full |
Neural network based method of a user identification by keyboard handwriting |
| title_fullStr |
Neural network based method of a user identification by keyboard handwriting |
| title_full_unstemmed |
Neural network based method of a user identification by keyboard handwriting |
| title_sort |
neural network based method of a user identification by keyboard handwriting |
| title_alt |
Метод идентификации пользователя по клавиатурному почерку на основе нейросети Метод ідентифікації користувача за клавіатурним почерком на основі нейромереж |
| description |
With the development of advanced technologies, the problem of information security is becoming increasingly relevant. Given the development of spyware and digital technology allow more effective attacks on computer systems, including corporate networks, confidentiality can only be achieved through the creation of comprehensive information security. And one of the main elements of such a security system is the subsystem, which provides the identification of the user of the computer. Traditional identification and authentication methods based on the use of cards, electronic keys or other portable identifiers, as well as passwords and access codes, have significant disadvantages. The main disadvantage of such methods is the ambiguity of the identified person. Existing methods of user identification by keyboard handwriting are accurate from 78 % to 93,59 % and built on multilevel neural networks, which affects the speed of their learning and as a result of the cost of more resources, so it is actual to increase the accuracy of identification and reduce the time to train the neural network and design the appropriate method. An experimental study was made of the possibility of using a two-level neural network with a built-in sigmoid activation function to improve the accuracy of user identification by keyboard handwriting and proposed a method based on this mathematical apparatus. A comparison of the proposed identification method with existing ones was also performed, which showed an increase in the accuracy of user identification by 1–15 %. The method of Saket Maheshwari and Vikram Pudi has similar accuracy indicators, but there are several significant differences between the proposed and the existing method: in their work Saket Maheshwari and Wikam Pudi used a five-level neural network; it took 9 minutes to study their neural network. In the proposed method, the time of training the neural network is 6 minutes, which is faster for 3 minutes and, as a result, is much more effective when used, since the user's identification time is reduced and high identification accuracy is on the same high level. |
| publisher |
Інститут проблем реєстрації інформації НАН України |
| publishDate |
2018 |
| url |
http://drsp.ipri.kiev.ua/article/view/142913 |
| work_keys_str_mv |
AT danyliukii neuralnetworkbasedmethodofauseridentificationbykeyboardhandwriting AT karpinetsvv neuralnetworkbasedmethodofauseridentificationbykeyboardhandwriting AT pryimakav neuralnetworkbasedmethodofauseridentificationbykeyboardhandwriting AT yaremchukye neuralnetworkbasedmethodofauseridentificationbykeyboardhandwriting AT kostiuchenkooi neuralnetworkbasedmethodofauseridentificationbykeyboardhandwriting AT danyliukii metodidentifikaciipolʹzovatelâpoklaviaturnomupočerkunaosnovenejroseti AT karpinetsvv metodidentifikaciipolʹzovatelâpoklaviaturnomupočerkunaosnovenejroseti AT pryimakav metodidentifikaciipolʹzovatelâpoklaviaturnomupočerkunaosnovenejroseti AT yaremchukye metodidentifikaciipolʹzovatelâpoklaviaturnomupočerkunaosnovenejroseti AT kostiuchenkooi metodidentifikaciipolʹzovatelâpoklaviaturnomupočerkunaosnovenejroseti AT danyliukii metodídentifíkacííkoristuvačazaklavíaturnimpočerkomnaosnovínejromerež AT karpinetsvv metodídentifíkacííkoristuvačazaklavíaturnimpočerkomnaosnovínejromerež AT pryimakav metodídentifíkacííkoristuvačazaklavíaturnimpočerkomnaosnovínejromerež AT yaremchukye metodídentifíkacííkoristuvačazaklavíaturnimpočerkomnaosnovínejromerež AT kostiuchenkooi metodídentifíkacííkoristuvačazaklavíaturnimpočerkomnaosnovínejromerež |
| first_indexed |
2024-04-21T19:33:53Z |
| last_indexed |
2024-04-21T19:33:53Z |
| _version_ |
1796974087080247296 |
| spelling |
drspiprikievua-article-1429132019-12-27T07:08:20Z Neural network based method of a user identification by keyboard handwriting Метод идентификации пользователя по клавиатурному почерку на основе нейросети Метод ідентифікації користувача за клавіатурним почерком на основі нейромереж Danyliuk, I. I. Karpinets, V. V. Pryimak, A. V. Yaremchuk, Y. E. Kostiuchenko, O. I. information security user authentication neural network keyboard handwriting time functions защита информации идентификация пользователя нейронная сеть клавиатурный почерк временные функции захист інформації ідентифікація користувача нейронна мережа клавіатурний почерк часові функції With the development of advanced technologies, the problem of information security is becoming increasingly relevant. Given the development of spyware and digital technology allow more effective attacks on computer systems, including corporate networks, confidentiality can only be achieved through the creation of comprehensive information security. And one of the main elements of such a security system is the subsystem, which provides the identification of the user of the computer. Traditional identification and authentication methods based on the use of cards, electronic keys or other portable identifiers, as well as passwords and access codes, have significant disadvantages. The main disadvantage of such methods is the ambiguity of the identified person. Existing methods of user identification by keyboard handwriting are accurate from 78 % to 93,59 % and built on multilevel neural networks, which affects the speed of their learning and as a result of the cost of more resources, so it is actual to increase the accuracy of identification and reduce the time to train the neural network and design the appropriate method. An experimental study was made of the possibility of using a two-level neural network with a built-in sigmoid activation function to improve the accuracy of user identification by keyboard handwriting and proposed a method based on this mathematical apparatus. A comparison of the proposed identification method with existing ones was also performed, which showed an increase in the accuracy of user identification by 1–15 %. The method of Saket Maheshwari and Vikram Pudi has similar accuracy indicators, but there are several significant differences between the proposed and the existing method: in their work Saket Maheshwari and Wikam Pudi used a five-level neural network; it took 9 minutes to study their neural network. In the proposed method, the time of training the neural network is 6 minutes, which is faster for 3 minutes and, as a result, is much more effective when used, since the user's identification time is reduced and high identification accuracy is on the same high level. Проведено экспериментальное исследование возможности использования двухуровневой нейросети с встроенной сигмоидной активационной функцией для улучшения точности идентификации пользователя по клавиатурному почерку и предложен метод на основе данного математического аппарата, а также проведено сравнение предложенного метода идентификации с существующими. Полученные результаты показали, что предложенный метод имеет лучшую точность идентификации на 1–15 %. Проведено експериментальне дослідження можливості використання дворівненої нейромережі з вбудованою сигмоїдною активаційною функцією для покращення точності ідентифікації користувача за клавіатурним почерком, а також проведено порівняння запропонованого методу ідентифікації з існуючими. Отримані результати показали, що запропонований метод має кращу точність ідентифікаціїна 1-15 %. Інститут проблем реєстрації інформації НАН України 2018-06-19 Article Article application/pdf http://drsp.ipri.kiev.ua/article/view/142913 10.35681/1560-9189.2018.20.2.142913 Data Recording, Storage & Processing; Vol. 20 No. 2 (2018); 68–76 Регистрация, хранение и обработка данных; Том 20 № 2 (2018); 68–76 Реєстрація, зберігання і обробка даних; Том 20 № 2 (2018); 68–76 1560-9189 uk http://drsp.ipri.kiev.ua/article/view/142913/140360 Авторське право (c) 2021 Реєстрація, зберігання і обробка даних |