DOI: 10.1007/978-3-540-74549-5_62
|View full text |Cite
|
Sign up to set email alerts
|

Keystroke Dynamics in a General Setting

Abstract: Abstract.It is well known that Keystroke Dynamics can be used as a biometric to authenticate users. But most work to date use fixed strings, such as userid or password. In this paper, we study the feasibility of using Keystroke Dynamics as a biometric in a more general setting, where users go about their normal daily activities of emailing, web surfing, and so on. We design two classifiers that appropriate for one-time and continuous authentication. We also propose a new Goodness Measure to compute the quality… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
20
0

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 41 publications
(20 citation statements)
references
References 10 publications
0
20
0
Order By: Relevance
“…Static version occurs generally before the authentication process can begin and that is before enrollment. In a dynamic version of enrollment, the users enroll during and/or after they have gained access to the system [9]- [11]. In our work the static version of enrollment is used.…”
Section: Introductionmentioning
confidence: 99%
“…Static version occurs generally before the authentication process can begin and that is before enrollment. In a dynamic version of enrollment, the users enroll during and/or after they have gained access to the system [9]- [11]. In our work the static version of enrollment is used.…”
Section: Introductionmentioning
confidence: 99%
“…The characteristics are represented by key events, i.e. pressing and releasing of a key as well as corresponding hold and transition periods [1,26]. Since these events can be measured in the millisecond range it is not possible to simulate another person's keystroke dynamics [10,34].…”
Section: A Methods and System Descriptionmentioning
confidence: 99%
“…Here system records all the key press and release timing and calculates the duration of depressed characters, latency time between various down and up key sequence latencies for each sample, then fmds out the actual timing template by applying some statistical methods. Then some features mining mechanism or distance based algorithm such as Euclidean distance, Manhattan distance, Manhattan distance with standard deviation, Mahalanobis distance, Bhattacharyya Distance as per Janakiraman, R. and Sim, T. [14], or Genetic algorithm, particle swan optimisation which is explained by Marcus, K. and Akila, M. [15] may be used to decide whether the user is valid. Thus we can minimise the probability of any off-line guessing attacks as rhythm of password is used, which cannot be copied even after watching it several times.…”
Section: Keystrokementioning
confidence: 99%