Authors
Zhiganov A.
|
Degree
|
Student, Kazan National Research Technical University A. N. Tupolev |
|---|---|
|
E-mail
|
Lesha.159@yandex.ru |
|
Location
|
Kazan |
|
Articles
|
Users authentication by the dynamics of keystrokes when using automatic proctoring systemsOnline courses and testing systems are becoming an integral part of distance learning systems today.
As an increasing number of people embrace online examinations, the need for validity protection
becomes more important. Personification is a huge challenge in online examinations administering
because of online users’ anonymity. In this article, we solved this problem through the use of keystroke
dynamics, which refers to the identification of users based on their typing patterns. Our work
confirmed the fact that it is possible to distinguish users according to their typing patterns. Our architecture
promises higher accuracy and reliability compared to other methods that use the dynamics of
keystrokes to distinguish between real and fake users, since it has 3 levels. The architecture contains of
a statistical level, machine learning level, and a logical comparison level in hierarchical order. When a
user signs up in the system, his typing data is automatically captured for use in templates generation.
The templates are used as references to continuously authenticate the user while taking an online examination.
An experiment was conducted, the research results showed that the accuracy of user authentication
was 97.5%. Also we found out that our architecture outperformed other decision in several
aspects. That aspects are also observed in our work.
Read more...
|
