Keystroke dynamics based user authentication using Histogram Gradient Boosting

Abstract

User authentication is a vital part of securing digital services and preventing unauthorized users from gaining access to the system. Nowadays, organizations use Multi-Factor Authentication (MFA) to provide robust protection by utilizing two or more identity procedures instead of using Single Factor Authentication (SFA) which became less secure. Keystroke dynamics is a behavioral biometric that examines a user's typing rhythm to determine the subject's legitimacy using the system. Keystroke dynamics have a minimal implementation cost and do not need special hardware in the authentication process since the gathering of typing data is reasonably straightforward and does not involve additional effort from the user. In this work, we present an efficient approach that uses the quantile transformation that transforms data distribution into uniform distribution which significantly reduces the impact of outlier and extreme values. Histogram Gradient Boosting is employed as the primary classifier for the training and testing phase. Our proposed approach is evaluated on Carnegie Mellon University (CMU) keystroke benchmark dataset which has achieved 97.96% of average accuracy and 0.014 of average equal error rate (EER) across all subjects which outperforms all the previous advances in both machine and deep learning approaches.

A Secure and Scalable Behavioral Dynamics Authentication Model

“…Accordingly, we propose a scalable dynamic behavioral authentication model incorporating future trends in information systems, specifically, trends in or toward (1) devices, (2) dynamic encryption standards, (3) assessing the emotional state of the authenticator, (4) the ubiquitous access to and usage of devices, and the option to (5) incorporate emerging technologies and solutions for low cost and increased functionality. The result, validated based on these five constructs, is a cost-effective and non-intrusive MFA system method to augment users' authentication and ensure data security while efficiently handling their typing errors [19]. The use of keystrokes itself validates the model owing to its simplicity and its ability to integrate seamlessly with passwords.…”

“…Among the world's privacy and security laws, the European Union General Data Protection Regulation (GDPR), adopted in 2016 and enacted on May 25, 2018, is the strongest [16], and a crucial aspect of compliance with this regulation is adequate authentication and authorization [17]. Accordingly, biometrics generated through KD has become a viable option to authenticate users for both security and surveillance purposes [18] given the minimal implementation cost of KD and lack of a need for special hardware since the gathering of typing data www.ijacsa.thesai.org is reasonably straightforward, requiring no additional effort by the user [19].…”

Efficient Convolutional Neural Network-Based Keystroke Dynamics for Boosting User Authentication

“…In [ 11 ], the main classifier used in the training and testing phase was Histogram Gradient Boosting (HGB), which relies on histograms to group continuous data into a fixed number of bins. By reducing the number of unique values for each feature to a smaller, more manageable set, this technique allows for faster and more efficient implementation of decision trees.…”

“… Comparison of accuracy with the related literature (from left to right: [ 17 ], [ 19 ], [ 21 ], [ 25 ], [ 26 ], [ 22 ], [ 20 ], [ 12 ], [ 11 ], [ 23 ]). …”

A Deep-Learning-Based Approach to Keystroke-Injection Payload Generation

“…Moreover, keystroke dynamics can be classified into two distinct types: fixed-text and free-text. The key difference between these two methods is the dataset that is used to authenticate a user [39,40]. Fixed-text authentication is mostly used as a second-factor or multi-factor authentication.…”