Benchmarking Touchscreen Biometrics for Mobile Authentication

Fiérrez, Julián; Pozo, Ada; Martinez-Diaz, Marcos; Galbally, Javier; Morales, Aythami

doi:10.1109/tifs.2018.2833042

Cited by 83 publications

(77 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [2] and [1], touch-gestures are used to authenticate but gestures are limited to swipes in a non-continuous architecture. Authors of [10] benchmark their touch-gesture authentication scheme against the state-of-the-art by using multiple touch-gesture datasets. The focus of the study is on swipe gestures and uses features derived from earlier studies that are not tailored to gesture typing.…”

Section: Related Workmentioning

confidence: 99%

“…The diverse differences in word-gestures for different words make them difficult to compare. Because we endeavour for our scheme to [20] Fierrez, et al [10] Kumar, et al [19] Jain and Kanhangad [15] Sitova, et al [24] Giuffrida, et al [12] Crawford and Ahmadzadeh [8] This work be word-agnostic (such that we do not require a classifier for each word) we work on reducing each word-gesture to generalised features that can be compared across words. In our scheme, when touch data is obtained from a word-gesture the gesture is processed to provide regions of interest for feature extraction.…”

Section: General Ideamentioning

confidence: 99%

See 1 more Smart Citation

A novel word-independent gesture-typing continuous authentication scheme for mobile devices

Smith-Creasey

Rajarajan

2019

Computers & Security

View full text Add to dashboard Cite

In this study we produce a new continuous authentication scheme for gesture-typing on mobile devices. Our scheme is the first scheme that authenticates gesture-typing interactions in a word-agnostic format. The scheme relies on groupings of features extracted from the word gesture after it has been reduced to parts common to all gestures. We show that movement sensors are also important in differentiating between users. We describe the feature extraction processes and analyse our proposed feature set. The unique process of our authentication scheme is presented and described. We collect our own gesture typing dataset including data collected during sitting, standing and walking activities for realism. We test our features against state-of-the-art touch-screen interaction features and compare feature extraction times on real mobile devices. Our scheme authenticates users with an equal error rate of 3.58% for a single word-gesture. The equal error rate is reduced to 0.81% when 3 word-gestures are used to authenticate.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: General Ideamentioning

confidence: 99%

A novel word-independent gesture-typing continuous authentication scheme for mobile devices

Smith-Creasey

Rajarajan

2019

Computers & Security

View full text Add to dashboard Cite

show abstract

“…The UMDAA-02 Dataset [18] is an unconstrained multimodal dataset with 44 subjects where 18 sensor observations were recorded across a two month period using a Nexus 5 mobile device. Authors of [18] have made the face modality and the touch-data modality [19] (a) (b) Fig. 3.…”

Section: Resultsmentioning

confidence: 99%

Quickest intrusion detection in mobile active user authentication

Perera

Patel

2016

2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

In this paper, we investigate how to detect intruders with low latency for Active Authentication (AA) systems with multiple-users. We extend the Quickest Change Detection (QCD) framework to the multiple-user case and formulate the Multiple-user Quickest Intruder Detection (MQID) algorithm. Furthermore, we extend the algorithm to the data-efficient scenario where intruder detection is carried out with fewer observation samples. We evaluate the effectiveness of the proposed method on two publicly available AA datasets on the face modality.

show abstract

“…Most traditional and widely deployed biometric solutions for person recognition are designed for access control or forensic scenarios. One important challenge in biometrics is how to properly integrate biometrics technologies in other application scenarios like mobile authentication [71,72], video surveillance [3], forensics [73], largescale ID [74], cloud biometrics or ubiquitous biometrics [75].…”

Section: Challenges In Biometrics: Role Of Mcsmentioning

confidence: 99%