Context-Aware Active Authentication Using Smartphone Accelerometer Measurements

Primo, Abena; Phoha, Vir V.; Kumar, Rajesh; Serwadda, Abdul

doi:10.1109/cvprw.2014.20

Cited by 99 publications

(59 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Active authentication systems deal with this issue by continuously monitoring the user identity after the initial access has been granted. Examples include systems based on screen touch gestures [63], gait recognition [64], and device movement patterns (as measured by the accelerometer) [65]. The development of cancelable active authentication systems is a nascent area of research.…”

Section: Discussionmentioning

confidence: 99%

Cancelable Biometrics: A review

Patel

Ratha

Chellappa

2015

IEEE Signal Process. Mag.

328

129

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Cancelable Biometrics: A review

Patel

Ratha

Chellappa

2015

IEEE Signal Process. Mag.

328

129

View full text Add to dashboard Cite

“…In Vera‐Rodriguez et al they use floor sensor–based scheme to identify a single‐target person and accomplish 90% to 97.5% accuracy. Wearable devices like smart mobiles and watches were used for collect gait information to human recognition . In Sprager and Zazula, they use over six human subjects' data in a wearable sensor‐based scheme and accomplish 90% accuracy.…”

Section: Related Workmentioning

confidence: 99%

Gait signals classification and comparison

Barua

Yang

Ren

et al. 2019

Int J Numerical Modelling

View full text Add to dashboard Cite

Use of wireless signal technology in sensing of human gait activity is a satisfactory example of device‐free sensing and effective in medical science to detect human motion–related diseases. Some prior research showed some potential detecting process of human walking gait from wireless channel information (WCI) using wireless signals. In this paper, we present comparison of three popular features reduction methods such as principal component analysis (PCA), kernel principal component analysis (KPCA), and linear discriminant analysis (LDA) using three classifications methods, support vector machine (SVM), k‐nearest neighbor (k‐NN), and decision tree (DT) in an absolutely equivalent situation for identifying walking gait signals. The analysis was carried out on the WCI‐based dataset where dataset was divided into four classes (normal gait, small gait, fast gait, and turn gait). Using dataset with the combination of methods (features reduction and classification), experimental results shows that all the combinations of PCA, KPCA, and LDA with three classifications achieve an average accuracy of gait identification is accordingly 86%, 79%, and 95%.

show abstract

“…In these examples, the difference in authentication accuracy was evaluated in specific usage environments, namely, different holding positions; however, the idea of the context awareness shown in [12], where an authentication algorithm is adjusted in accordance with a user's context, has still yet to be reached. Some examples of authentication algorithms that consider context awareness are shown in [17], [18]. Primo et al [18] focused on 55 features that can be obtained from an accelerometer on a smartphone and clarified the effective features corresponding to the holding positions of the smartphone and showed that highly reliable authentication can be achieved by selecting the appropriate features for each holding position.…”

Section: Related Workmentioning

confidence: 99%

“…Some examples of authentication algorithms that consider context awareness are shown in [17], [18]. Primo et al [18] focused on 55 features that can be obtained from an accelerometer on a smartphone and clarified the effective features corresponding to the holding positions of the smartphone and showed that highly reliable authentication can be achieved by selecting the appropriate features for each holding position. Moreover, Hayashi et al [17] proposed a scheme for selecting an appropriate authentication method to meet security demands.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Toward More Secure and Convenient User Authentication in Smart Device Era

Yoshida

Ohki

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARY With the rapid spread of smart devices, such as smartphones and tablet PCs, user authentication is becoming increasingly important because various kinds of data concerning user privacy are processed within them. At present, in the case of smart devices, password-based authentication is frequently used; however, biometric authentication has attracted more attention as a user authentication technology. A smart device is equipped with various sensors, such as cameras, microphones, and touch panels, many of which enable biometric information to be obtained. While the function of biometric authentication is available in many smart devices, there remain some problems to be addressed for more secure and convenient user authentication. In this paper, we summarize the current problems with user authentication on smart devices and propose a novel user authentication system based on the concept of context awareness to resolve these problems. We also present our evaluation of the performance of the system by using biometric information that was acquired from smart devices. The evaluation demonstrates the effectiveness of our system.

show abstract

Context-Aware Active Authentication Using Smartphone Accelerometer Measurements

Cited by 99 publications

References 17 publications

Cancelable Biometrics: A review

Cancelable Biometrics: A review

Gait signals classification and comparison

Toward More Secure and Convenient User Authentication in Smart Device Era

Contact Info

Product

Resources

About