Analyzing the Effectiveness of Touch Keystroke Dynamic Authentication for the Arabic Language

The keystroke dynamic authentication (KDA) technique was proposed in the literature to develop a more effective authentication technique than traditional methods. KDA analyzes the rhythmic typing of the owner on a keypad or keyboard as a source of verification. In this study, we extend the findings of the system by analyzing the existing literature and validating its effectiveness in Arabic. In particular, we examined the effectiveness of the KDA system in Arabic for touchscreen-based digital devices using two KDA classes: fixed and free text. To this end, a KDA system was developed and applied to a selected device operating on the Android platform, and various classification methods were used to assess the similarity between log-in and enrolment sessions. The developed system was experimentally evaluated. The results showed that using Arabic KDA on touchscreen devices is possible and can enhance security. It attains a higher accuracy with average equal error rates of 0.0% and 0.08% by using the free text and fixed text classes, respectively, implying that free text is more secure than fixed text.

Age and Gender as Cyber Attribution Features in Keystroke Dynamic-Based User Classification Processes

Keystroke dynamics are used to authenticate users, to reveal some of their inherent or acquired characteristics and to assess their mental and physical states. The most common features utilized are the time intervals that the keys remain pressed and the time intervals that are required to use two consecutive keys. This paper examines which of these features are the most important and how utilization of these features can lead to better classification results. To achieve this, an existing dataset consisting of 387 logfiles is used, five classifiers are exploited and users are classified by gender and age. The results, while demonstrating the application of these two characteristics jointly on classifiers with high accuracy, answer the question of which keystroke dynamics features are more appropriate for classification with common classifiers.

Identification of the Exclusivity of Individual’s Typing Style Using Soft Biometric Elements

Biometric is used as a main security fence in a computer system. The unique characteristics of a person can be distinguished from each other. Human’s biometrics can be categorized into three types: morphological, biological and behavioural. Morphological biometrics uses physical features for recognition. Biological biometrics used to identify user based on biological features. Behavioural biometrics such as gender, culture, height and weight can be used as an additional security measure within a system. These biometric behavioural features are also known as soft biometric. This study uses soft biometric elements (gender, culture, region of birth and educational level) in the keystroke dynamic study to distinguish typing patterns in each of these categories. The Support Vector Machine (SVM) classification method is used to perform this classification for soft biometric identification. The results of this study have shown that soft biometrics in keystroke dynamic can be used to distinguish group of individuals typing.

Keystroke Dynamic Authentication Using Combined MHR (Mean of Horner’s Rules) and Standard Deviation

Keystroke Dynamic Authentication used a behavior to authenticate the user and one of biometric authentication. The behavior used a typing speed a character on the keyboard and every user had a unique behavior in typing. To improve classification between user and attacker of Keystroke Dynamic Authentication in this research, we proposed a combination of MHR (Mean of Horner’s Rules) and standard deviation. The results of this research showed that our proposed method gave a high accuracy (93.872%) than the previous method (75.388% and 75.156%). This research gave an opportunity to implemented in real login system because our method gave the best results with False Acceptance Rate (FAR) is 0.113. The user can be used as a simple password and ignore a worrying about an account hacking in the system.