Performance Evaluation of Behavioral Biometric Systems

Cherifi, Fouad; Hemery, Baptiste; Giot, Romain; Pasquet, Marc; Rosenberger, Christophe

doi:10.4018/978-1-60566-725-6.ch003

Cited by 19 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…a high probability to be unused). Comparing biometric systems can be realized within three contexts [5] :…”

Section: A General Methodologiesmentioning

confidence: 99%

“…They applied their method for creating the database used in their paper, but, sadly, did not make it available. In [5], we argue that to create a good behavioural biometric database the number of required sessions have to be superior or equal to three, that these sessions must be spaced in time, the population must be large and diversified. These requirements were not always fit in previous researches.…”

Section: Contributionmentioning

confidence: 99%

See 1 more Smart Citation

GREYC keystroke: A benchmark for keystroke dynamics biometric systems

Giot¹,

El-Abed²,

Rosenberger³

2009

2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems

135

108

View full text Add to dashboard Cite

Even if the market penetration rate of biometric technologies is still far below its potential, many biometric systems are used in our daily real-life. One of the main reasons to its low proliferation is the lack of a generic and complete approach that quantifies the performance of biometric systems taking into account individuals' perception among the process. Among all the existing biometric modalities, authentication systems based on keystroke dynamics are particularly interesting. Many researchers proposed in the last decades some algorithms to increase the efficiency of this approach. Nevertheless, none significant benchmark is available and commonly used in the state of the art to compare them by using a similar and rigorous protocol. We propose in this paper: a benchmark testing suite composed of a database and a software that are available for the scientific community for the evaluation of keystroke dynamics based systems. Performance evaluation of various keystroke dynamics methods tested on the database is available in [1].

show abstract

“…a high probability to be unused). Comparing biometric systems can be realized within three contexts [5] :…”

Section: A General Methodologiesmentioning

confidence: 99%

Section: Contributionmentioning

confidence: 99%

GREYC keystroke: A benchmark for keystroke dynamics biometric systems

Giot¹,

El-Abed²,

Rosenberger³

2009

2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems

135

108

View full text Add to dashboard Cite

show abstract

“…Since then different approaches for studying the problem have been proposed with varying experimental setups and conclusions. It is not until recently, with the emerging data mining algorithms, that methods for establishing a performance comparative framework between those techniques are investigated [13]. Various approaches in the literature have differed in the size of the collected data per user, number of samples, method of collecting data, number of users, environment conditions (controlled or non-controlled) and the choice of classification method.…”

Section: Related Workmentioning

confidence: 99%

Comparison between mixed binary classification and voting technique for active user authentication using mouse dynamics

Khalifa

Hassan

Khalid

et al. 2015

2015 International Conference on Computing, Control, Networking, Electronics and Embedded Systems Engineering (ICCNEEE)

View full text Add to dashboard Cite

The rapid proliferation of computing processing power has facilitated a rise in the adoption of computers in various aspects of human lives. From education to shopping and other everyday activities to critical applications in finance, banking and, recently, degree awarding online education. Several approaches for user authentication based on Behavioral Biometrics (BB) were suggested in order to identify unique signature/footprint for improved matching accuracy for genuine users and flagging for abnormal behaviors from intruders. In this paper we present a comparison between two classification algorithms for identifying users' behavior using mouse dynamics. The algorithms are based on support vector machines (SVM) classifier allowing for direct comparison between different authentication-based metrics. The voting technique shows low False Acceptance Rate(F AR) and noticeably small learning time; making it more suitable for incorporation within different authentication applications.

show abstract

“…A lot of the newer benchmarks have respected constraints on the way of creating good behavioral biometrics databases (in terms of number of sessions, duration between each session, number of individuals and so on [Cherifi et al, 2009]). In this section, we present the list of existing benchmarks from the state-of-the-art.…”

Section: • Synthetic Benchmarksmentioning

confidence: 99%

Rhu Keystroke Touchscreen Benchmark

El-Abed

Dafer

Rosenberger

2018

2018 International Conference on Cyberworlds (CW)

View full text Add to dashboard Cite

Biometric systems are currently widely used in many applications to control and verify individual's identity. Keystroke dynamics modality has been shown as a promising solution that would be used in many applications such as e-payment and banking applications. However, such systems suffer from several performance limitations (such as crossdevices problem) that prevent their widespread of use in real applications. The objective of this paper is to provide researchers and developers with a public touchscreen-based benchmark collected using a mobile phone and a tablet (both portrait and landscape orientation each). Such a benchmark can be used to assess keystroke-based matching algorithms. Furthermore, It is mainly developed to measure the robustness of keystroke matching algorithms vis-à-vis cross-devices and orientation variations. An online visualizer for the database is also given to researchers allowing them to visualize the acquired keystroke signals.

show abstract

Performance Evaluation of Behavioral Biometric Systems

Cited by 19 publications

References 19 publications

GREYC keystroke: A benchmark for keystroke dynamics biometric systems

GREYC keystroke: A benchmark for keystroke dynamics biometric systems

Comparison between mixed binary classification and voting technique for active user authentication using mouse dynamics

Rhu Keystroke Touchscreen Benchmark

Contact Info

Product

Resources

About