User identification via keystroke characteristics of typed names using neural networks

Brown, Mark; Rogers, Samuel J.

doi:10.1006/imms.1993.1092

Cited by 146 publications

(58 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Thirty repetitions of each keyword were included, to ensure enough data for classification. The words selected are listed in Table 2, along with the number of inter-keystroke latencies that they involve and the number of samples used for training and testing after outliers were removed (a standard procedure for keystroke analysis studies [7][8][9][10][11][12][13][14][15]. Literature has showed that attempts to perform dynamic analysis on keystroke dynamics [13,14] did not yield satisfactory results.…”

Section: Methodsmentioning

confidence: 99%

Keystroke Analysis for Thumb-based Keyboards on Mobile Devices

Karatzouni

Clarke

2007

New Approaches for Security, Privacy and Trust in Complex Environments

View full text Add to dashboard Cite

Abstract. The evolution of mobile networking has opened the door to a wide range of service opportunities for mobile devices, increasing at the same time the sensitivity of the information stored and access through them. Current PINbased authentication has proved to be an insufficient and an inconvenient approach. Biometrics have proven to be a reliable approach to identity verification and can provide a more robust means of security, as they rely upon personal identifiers. Amongst various biometric techniques available, keystroke analysis combines features that can offer a cost effective, nonintrusive and continuous authentication solution for mobile devices. This research has been undertaken in order to investigate the performance of keystroke analysis on thumb-based keyboards that are being widely deployed upon PDA's and Smartphone devices. The investigation sought to authenticate users whilst typing text messages, using two keystroke characteristics, the inter-keystroke latency and hold-time. The results demonstrate the approach to be promising, achieving an average EER=12.2% with the inter-keystroke latency based upon 50 participants. Uniquely to this tactile environment however, the hold-time characteristic, did not prove to be a reliable feature to be utilised.

show abstract

Section: Methodsmentioning

confidence: 99%

Keystroke Analysis for Thumb-based Keyboards on Mobile Devices

Karatzouni

Clarke

2007

New Approaches for Security, Privacy and Trust in Complex Environments

View full text Add to dashboard Cite

show abstract

“…Previous works [3,18,20] used these two components in their verification systems. However, the initial sample sets of [3,20] did not provide enough data to ascertain whether the use of the two separate orthogonal digraph components added significant predictive power to the more traditional key down-to-down measure. Substantially improved performance results based on using the bivariate measure of latency with an appropriate distance measure were achieved by [18].…”

Section: The Current State Of Keystroke Dynamicsmentioning

confidence: 99%

“…Some neural network approaches [1,3,12] have also been undertaken in the last few years. While the back-propagation models used yield favorable performance results on small databases, neural networks have a fundamental limitation in that each time a new user is introduced into the database, the network must be retrained.…”

Section: The Current State Of Keystroke Dynamicsmentioning

confidence: 99%

Keystroke dynamics as a biometric for authentication

Monrose

Rubin

2000

Future Generation Computer Systems

575

301

View full text Add to dashboard Cite

More than ever before the Internet is changing computing as we know it. Global access to information and resources is becoming an integral part of nearly every aspect of our lives. Unfortunately, with this global network access comes increased chances of malicious attack and intrusion. In an effort to confront the new threats unveiled by the networking revolution of the past few years reliable, rapid, and unintrusive means for automatically recognizing the identity of individuals are now being sought. In this paper we examine an emerging non-static biometric technique that aims to identify users based on analyzing habitual rhythm patterns in the way they type.

show abstract

“…D'Souza's experiment weighted the latencies to reduce false acceptances [4]. Brown and Rogers [3] and Obaidat and Sadoun [15] used short name strings for user verification. Dynamic shuffling was also evaluated as a process applied to training samples for neural networks as a means of enhancing sample classification and reducing false acceptance and rejection rates during keystroke analysis [3].…”

Section: Introductionmentioning

confidence: 99%

“…Brown and Rogers [3] and Obaidat and Sadoun [15] used short name strings for user verification. Dynamic shuffling was also evaluated as a process applied to training samples for neural networks as a means of enhancing sample classification and reducing false acceptance and rejection rates during keystroke analysis [3]. Recent work by Gunnetti and Picardi [8] suggest that if short inputs do not provide sufficient timing C3.2 information, and if long predefined texts entered repeatedly are unacceptable, we are left with only one possible solution, which is using the typing rhythms users show during their normal interaction with a computer; in other words, deal with the keystroke dynamics of free text.…”

Section: Introductionmentioning

confidence: 99%