Biometric Authentication for Wearables

Sellahewa, Harin; Ibrahim, Nasiru; Zeadally, Sherali

doi:10.1007/978-3-319-98734-7_14

Cited by 7 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, because many wearable devices can be easily removed by users and worn by somebody else, the use of single-time authentication methods such as passwords are not enough to guarantee who is using a wearable device. To enforce authentication, various user authentication methods have been proposed based on biometrics [180], multifactor authentication mechanisms [76,181], and multiple wearable devices [182,183].…”

Section: Vulnerability Description Examples Of Attacksmentioning

confidence: 99%

Recent Advances in Wearable Sensing Technologies

Pérez

Zeadally

2021

Sensors

Self Cite

View full text Add to dashboard Cite

Wearable sensing technologies are having a worldwide impact on the creation of novel business opportunities and application services that are benefiting the common citizen. By using these technologies, people have transformed the way they live, interact with each other and their surroundings, their daily routines, and how they monitor their health conditions. We review recent advances in the area of wearable sensing technologies, focusing on aspects such as sensor technologies, communication infrastructures, service infrastructures, security, and privacy. We also review the use of consumer wearables during the coronavirus disease 19 (COVID-19) pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), and we discuss open challenges that must be addressed to further improve the efficacy of wearable sensing systems in the future.

show abstract

Section: Vulnerability Description Examples Of Attacksmentioning

confidence: 99%

Recent Advances in Wearable Sensing Technologies

Pérez

Zeadally

2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…The SVM classifier was initially designed to classify data instants into binary classes. The extension of SVM methods for multiclass classification problems has gained significant attention [37]. There are three main methods for implementing a multiclass SVM classifier, including Multiclass ranking SVMs, the pairwise coupling and one formulation for all.…”

Section: Ecg and Gait Classificationmentioning

confidence: 99%

“…In this work, we have followed the match score level fusion to set up both modalities and its has a proven performance record. The authentication via the modern smartwatch contains multiple sensors offers a user-friendly alternative to common authentication methods on smartphones [37]. It has the great advantage that the authentication can be performed without user interaction.…”

Section: Introductionmentioning

confidence: 99%

An Improved Behavioral Biometric System based on Gait and ECG signals

Guelta¹,

Tlemsani²,

Chouraqui³

et al. 2019

IJIES

View full text Add to dashboard Cite

This paper presents multi-modal biometric authentication approach using gait and electrocardiogram (ECG) signals, which can diminish the drawback of unimodal biometric approach as well as to improve authentication system performance. In acquisition phase, data sets are collected from three different databases, ECG-ID, MIT-BIH Arrhythmia database and UCI Machine Learning Repository (Gait). In Feature extraction phase of both signals (ECG and Gait) is performed by using 1D-local binary pattern. Features are obtained by merging two modalities as one feature. In classification approach, three classifiers are developed to classify subjects. K-nearest neighbour (KNN), relying on Euclidean distance, PNN (Probabilistic Neural Network), RBF (Radial Basis Function) and Support Vector Machine (SVM), relying on One-against-all (OAA). The proposed multimodal system has been tested over 18 subjects, and its identification accuracy was about 100%. Our result demonstrate that our approach outperforms rather than unimodal biometric system in terms of Correct Recognition Rate, Equal Error Rate, False Acceptance Rate and False Reject Rate.

show abstract

“…While the task of user authentication using sensors built into smartphones has been well addressed in the literature, studies on wearable motion sensor-based biometrics are very few [ 10 , 11 ]. The use of wearable motion sensors for user authentication is particularly valuable: first, the incorporated wearable devices for user authentication can come in different forms, such as smartwatches, gloves, or shoe insoles [ 10 , 11 ], which helps to reduce the dependence of user authentication on smartphone devices; secondly, it is important to detect an interaction between fingers and hands on hand-object manipulations [ 12 ], but built-in smartphone sensors cannot detect finger movements; thirdly, it enables silent user authentication through the daily use of objects the way the user manipulates objects “in-the-wild” [ 13 ] (e.g., lifting a cup or spreading butter with a knife).…”

Section: Introductionmentioning

confidence: 99%

Deep Residual Networks for User Authentication via Hand-Object Manipulations

Choi

Ryu

Kim

2021

Sensors

View full text Add to dashboard Cite

With the ubiquity of wearable devices, various behavioural biometrics have been exploited for continuous user authentication during daily activities. However, biometric authentication using complex hand behaviours have not been sufficiently investigated. This paper presents an implicit and continuous user authentication model based on hand-object manipulation behaviour, using a finger-and hand-mounted inertial measurement unit (IMU)-based system and state-of-the-art deep learning models. We employed three convolutional neural network (CNN)-based deep residual networks (ResNets) with multiple depths (i.e., 50, 101, and 152 layers) and two recurrent neural network (RNN)-based long short-term memory (LSTMs): simple and bidirectional. To increase ecological validity, data collection of hand-object manipulation behaviours was based on three different age groups and simple and complex daily object manipulation scenarios. As a result, both the ResNets and LSTMs models acceptably identified users’ hand behaviour patterns, with the best average accuracy of 96.31% and F1-score of 88.08%. Specifically, in the simple hand behaviour authentication scenarios, more layers in residual networks tended to show better performance without showing conventional degradation problems (the ResNet-152 > ResNet-101 > ResNet-50). In a complex hand behaviour scenario, the ResNet models outperformed user authentication compared to the LSTMs. The 152-layered ResNet and bidirectional LSTM showed an average false rejection rate of 8.34% and 16.67% and an equal error rate of 1.62% and 9.95%, respectively.

show abstract

Biometric Authentication for Wearables

Cited by 7 publications

References 15 publications

Recent Advances in Wearable Sensing Technologies

Recent Advances in Wearable Sensing Technologies

An Improved Behavioral Biometric System based on Gait and ECG signals

Deep Residual Networks for User Authentication via Hand-Object Manipulations

Contact Info

Product

Resources

About