Equalization of keystroke timing histograms for improved identification performance

Montalvão, Jugurta; Almeida, Carlos Augusto S.; Freire, Eduardo Oliveira

doi:10.1109/its.2006.4433337

Cited by 22 publications

(13 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The benefit of using these data and methods is a valid comparison with the results in this work. 1 To our knowledge, the only other researchers to make keystroke data publicly available through the Web are Montalvão et al [15]. From discussion with colleagues, we understand that other data sets are forthcoming, and we welcome this trend since the availability of a diverse set of public data will boost progress in this field.…”

Section: Shared Data and Methodsmentioning

confidence: 97%

Comparing anomaly-detection algorithms for keystroke dynamics

Killourhy

Maxion

2009

2009 IEEE/IFIP International Conference on Dependable Systems &Amp; Networks

407

354

View full text Add to dashboard Cite

show abstract

Section: Shared Data and Methodsmentioning

confidence: 97%

Comparing anomaly-detection algorithms for keystroke dynamics

Killourhy

Maxion

2009

2009 IEEE/IFIP International Conference on Dependable Systems &Amp; Networks

407

354

View full text Add to dashboard Cite

show abstract

“…Users Performance Gunetti and Picardi [10] 205 13% (ERR) SVM [11] 100 6.95% (EER) Nearest neighbour [12] 51 9.96% (ERR) Hidden Markov Model [13] 20 3.6% (EER) Bleha (with equalization) [14] 47 6.2% (EER) Manhattan Distance [15] 51 7.1% (EER) Random Forests [16] 53 1% (FAR), 14% (FRR) Tree-based [17] 12 0% (FAR), 3.47% (FRR) R Measure [18] 205 0.005% (FAR), 5% (FRR) AAMLP [4] 21 0% (FAR), 0.25 % (FRR)…”

Section: Classifiermentioning

confidence: 99%

Negative Selection with High-Dimensional Support for Keystroke Dynamics

Pisani

Lorena

2012

2012 Brazilian Symposium on Neural Networks

View full text Add to dashboard Cite

Computing and communication systems have been expanding and bringing a number of advancements to our way of life. However, this technological evolution has also contributed to the rise of the identity theft, mainly due to the advent of the digital identity. An alternative to overcome this problem is by the analysis of the user behavior, known as behavioral intrusion detection. Among the possible aspects to be analysed, this work focuses on the keystroke dynamics, which consists of recognizing users by their typing rhythm. This paper draws a comparison between some novelty detectors applied to keystroke dynamics: immune negative selection algorithms and auto-associative neural networks. Issues regarding the use of negative selection in high dimensional spaces are discussed and an alternative to deal with this problem is presented.

show abstract

“…Texts for use in creating a biometric marker can be as short as passwords and single phrase/sentences [20] or as long as a freely entered essay or prose [10,22].…”

Section: Accepted Manuscriptmentioning

confidence: 99%