2021
DOI: 10.1016/j.neucom.2020.02.122
|View full text |Cite
|
Sign up to set email alerts
|

Continuous authentication with a focus on explainability

Abstract: Traditional explicit authentication mechanisms, in which the device remains unlocked after the introduction of some kind of password, are slowly being complemented with the so-called implicit or continuous authentication mechanisms. In the latter, the user is constantly monitored in one or more ways, in search for signs of unauthorized access, which may happen if a third party has access to the phone after it has been unlocked. There are some different forms of continuous authentication, some of which based on… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(5 citation statements)
references
References 8 publications
0
5
0
Order By: Relevance
“…The lowest EER from the studies we re-implemented was [58] with an average of 17.48% EER over all the machine learning algorithms examined. We attribute the low performance of some feature sets such as [44] (28.02%) to the small number of features included. However, the final model of the study uses additional features from sensor data which could result in much better overall performance.…”
Section: Resultsmentioning
confidence: 99%
“…The lowest EER from the studies we re-implemented was [58] with an average of 17.48% EER over all the machine learning algorithms examined. We attribute the low performance of some feature sets such as [44] (28.02%) to the small number of features included. However, the final model of the study uses additional features from sensor data which could result in much better overall performance.…”
Section: Resultsmentioning
confidence: 99%
“…The best performing of the studies we re-implemented was Xu et al [58] with an average of 17.48% EER over all the machine learning algorithms examined. We attribute the low performance of some feature sets such as Rocha et al [44] (28.02%) to the small number of features included. However, the final model of the study uses additional features from sensor data which could result in much better overall performance.…”
Section: Resultsmentioning
confidence: 99%
“…Such metrics are accuracy, f-measure, precision, false acceptance rate, recall, false-negative rate, and error rate. Moreover, the recent existing approaches like Static Dynamic Algorithm (SDA) [21], Improve Keystroke Accuracy replica (IKA) [22], and fingerprint of EM signal model (FEM) [9]. The process of the IKA replica is based on authentication and improve accuracy using the free text of keystroke dynamic but developed CRNM technique continuously authenticate the user actions based on keystroke and mouse dynamics.…”
Section: Performance Metricsmentioning
confidence: 99%
“…There are numerous advancements at present to estimate the own users [11]. In addition, an Authentication tends to distinguish each and every client's framework and execute program with those clients [22]. It is the obligation of the Operating System to make a security framework and guarantee of a client who is running in the specific program [8].…”
Section: Introductionmentioning
confidence: 99%