Normalizing variations in feature vector structure in keystroke dynamics authentication systems

Syed, Zahid; Banerjee, Sean; Čukić, Bojan

doi:10.1007/s11219-014-9263-1

Cited by 11 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The KDA method can be implemented in two distinct ways: static and dynamic (Furnell, Morrissey, Sanders, & Stockel, 1996;Gunetti & Picardi, 2005). The idea of different keystroke sequences for a single word has been introduced to seek the typing variance between various keystroke sequences of the word (Syed, Banerjee, & Cukic, 2016). This method suggests that different keystroke sequences can hold enough discriminative data to authenticate legal clients efficiently, and can be employed to both static and dynamic mode of authentication systems.…”

Section: Keystroke Dynamics Based Authenticationmentioning

confidence: 99%

“…The study concluded multiple inferences which were; PC keyboard is the best device to capture the keystrokes, the authentication accuracy was enhanced by increasing character length or sample size, and relative (R) + absolute (A) measures reported the best performing algorithm. The event sequences based KDA algorithm was introduced and implemented in both static and dynamic modes (Syed et al, 2016). The feature normalization presented in (Syed et al, 2016) had many advantages such as simplicity, faster search, and retrieval of n-graphs.…”

Section: Keystroke Dynamics Based Authenticationmentioning

confidence: 99%

“…The event sequences based KDA algorithm was introduced and implemented in both static and dynamic modes (Syed et al, 2016). The feature normalization presented in (Syed et al, 2016) had many advantages such as simplicity, faster search, and retrieval of n-graphs. Furthermore, the research suggested that the proposed KDA had better authentication accuracy, however none of the results showed any evidences for the actual accuracy of the system.…”

Section: Keystroke Dynamics Based Authenticationmentioning

confidence: 99%

“…Thorough study of existing literature, with the exception of works conducted by (Gunetti & Picardi, 2005;Kim et al, 2018), have suggested that most KDA methods presented in the articles were constrained by high EER and low authentication accuracy (Ahmed & Traore, 2014;Kang & Cho, 2015;Leggett et al, 1991;Mondal & Bours, 2017;Syed et al, 2016). The significant contributions of the proposed study are the inclusion of three more timing features, sole user database with limited password length, empirical thresholding algorithm, and database update rule.…”

Section: Contribution Of the Workmentioning

confidence: 99%

See 3 more Smart Citations

Applying Empirical Thresholding Algorithm for a Keystroke Dynamics Based Authentication System

Venugopal

Viji²

2019

JICT

View full text Add to dashboard Cite

Through the application of a password-based authentication technique, users are granted permission to access a secure system when the username and password matches with that logged in database of the system. Furthermore, anyone who provides the correct username and password of a valid user will be able to log in to the secure network. In current circumstances, impostors can hack the system to obtain a user's password, while it has also been easy to find out a person's private password. Thus, the existing structure is exceptionally flawed. One way to strengthen the password-based authentication technique, is by keystroke dynamics. In the proposed keystroke dynamics based authentication system, despite the password match, the similarity between the typing pattern of the typed password and password samples in the training database are verified. The timing features of the user's keystroke dynamics are collected to calculate the threshold values. In this paper, a novel algorithm is proposed to authenticate the legal users based on the empirical threshold values. The first step involves the extraction of timing features from the typed password samples. The password training database for each user is constructed using the extracted features. Moreover, the empirical threshold limits are calculated from the timing features in the database. The second step involves user authentication by applying these threshold values.

show abstract

Section: Keystroke Dynamics Based Authenticationmentioning

confidence: 99%

Section: Keystroke Dynamics Based Authenticationmentioning

confidence: 99%

Section: Keystroke Dynamics Based Authenticationmentioning

confidence: 99%

Section: Contribution Of the Workmentioning

confidence: 99%

See 2 more Smart Citations

Applying Empirical Thresholding Algorithm for a Keystroke Dynamics Based Authentication System

Venugopal

Viji²

2019

JICT

View full text Add to dashboard Cite

show abstract

“…Early work of the usage of typing patterns for authentication was directed at the static context. For example, static authentication with respect to the typing pattern, the rhythm, found when users typed in their credentials (password and username, or pin number) [4][5][6][7]. This can be referred to as Keystroke Static Authentication (KSA), static in the sense that the keys being pressed are predefined, or simply fixed.…”

Section: Introductionmentioning

confidence: 99%

Iterative Keystroke Continuous Authentication: A Time Series Based Approach

2018

View full text Add to dashboard Cite

Keyboard typing patterns are a form of behavioural biometric that can be usefully employed for the purpose of user authentication. The technique has been extensively investigated with respect to the typing of fixed texts such as passwords and pin numbers, so-called static authentication. The typical approach is to compare a current "typing sample" with a typing template expressed in terms of a feature vector comprised of keystroke dynamics. The feature vector approach has also been applied in the context of continuous authentication where features are extracted from free typing. However, the use of feature vectors for keystroke continuous authentication entails a number of disadvantages, mostly associated with the size of the feature vectors and their generation, which need to capture a large number of features to be effective; thus making the technique unsuitable for iterative (real-time) authentication as would be required in the case of, for example, online assessments. To address this issue, a mechanism whereby iterative real-time keystroke continuous authentication can be achieved is proposed, by considering typing behaviour as a form of time series, that avoids the disadvantages associated with the feature vector approach. The reported experimental results show a significantly improved performance using the proposed method in comparison with the feature vector based technique.

show abstract