Attribute-based continuous user authentication on mobile devices

Samangouei, Pouya; Patel, Vishal M.; Chellappa, Rama

doi:10.1109/btas.2015.7358748

Cited by 47 publications

(36 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among the AA techniques, the most explored are based on faces [10], [34], touch/swipe signature [37], multi-modal fusion [42], gait [8] and device movementpatterns/accelerometer [30], [6]. Face-based authentication, though most accurate, requires more computational power and can cause faster battery drain if the images are captured frequently.…”

Section: Previous Workmentioning

confidence: 99%

“…Faces captured by the front camera (and also screen touch data) of University of Maryland Active Authentication Dataset (UMDAA-01) [42] [34] of 50 users are unconstrained and hence presents a more realistic and challenging scenario for face-based continuous authentication where partially visible, frontal and non-frontal faces under various illumination conditions are available. In [23] and [36], the authors introduced facial segment-based face detection (FSFD) method and deep feature-based face detection for UMDAA-01-FD which is a small annotated subset of the UMDAA-01 dataset, respectively, and showed that the partial face detection capabilities of these methods make them suitable candidates for mobile front-camera face detection.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Active user authentication for smartphones: A challenge data set and benchmark results

Mahbub

Sarkar

Patel

et al. 2016

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

Self Cite

View full text Add to dashboard Cite

In this paper, automated user verification techniques for smartphones are investigated. A unique non-commercial dataset, the University of Maryland Active Authentication Dataset 02 (UMDAA-02) for multi-modal user authentication research is introduced. This paper focuses on three sensors -front camera, touch sensor and location service while providing a general description for other modalities. Benchmark results for face detection, face verification, touch-based user identification and location-based nextplace prediction are presented, which indicate that more robust methods fine-tuned to the mobile platform are needed to achieve satisfactory verification accuracy. The dataset will be made available to the research community for promoting additional research.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Active user authentication for smartphones: A challenge data set and benchmark results

Mahbub

Sarkar

Patel

et al. 2016

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…accuracy not reported facial attributes can be used as ancillary (or soft) information for face recognition systems, and can help in reducing the identity search space. Existing research in the literature has shown substantial improvement upon incorporating ancillary information for the task of person identification (Kumar et al, 2009;Samangouei et al, 2015;Mittal et al, 2017). Fig.…”

Section: Introductionmentioning

confidence: 99%

Residual Codean Autoencoder for Facial Attribute Analysis

Sethi

Singh

et al. 2019

Pattern Recognition Letters

View full text Add to dashboard Cite

Facial attributes can provide rich ancillary information which can be utilized for different applications such as targeted marketing, human computer interaction, and law enforcement. This research focuses on facial attribute prediction using a novel deep learning formulation, termed as R-Codean autoencoder. The paper first presents Cosine similarity based loss function in an autoencoder which is then incorporated into the Euclidean distance based autoencoder to formulate R-Codean. The proposed loss function thus aims to incorporate both magnitude and direction of image vectors during feature learning. Further, inspired by the utility of shortcut connections in deep models to facilitate learning of optimal parameters, without incurring the problem of vanishing gradient, the proposed formulation is extended to incorporate shortcut connections in the architecture. The proposed R-Codean autoencoder is utilized in facial attribute prediction framework which incorporates patch-based weighting mechanism for assigning higher weights to relevant patches for each attribute. The experimental results on publicly available CelebA and LFWA datasets demonstrate the efficacy of the proposed approach in addressing this challenging problem.

show abstract

“…Stylometry, GPS location, web browsing behavior, and application usage patterns were used in [13] for active authentication. Face-based continuous user authentication on mobile devices has also been proposed in [14], [10], [23], and [28,29]. Different modalities such as speech [23], Gait [7], touch [37] have been fused with faces.…”

Section: Introductionmentioning

confidence: 99%

Convolutional neural networks for attribute-based active authentication on mobile devices

Samangouei

Chellappa

2016

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

Self Cite

View full text Add to dashboard Cite

We present a Deep Convolutional Neural Network (DCNN) architecture for the task of continuous authentication on mobile devices. To deal with the limited resources of these devices, we reduce the complexity of the networks by learning intermediate features such as gender and hair color instead of identities. We present a multi-task, partbased DCNN architecture for attribute detection that performs better than the state-of-the-art methods in terms of accuracy. As a byproduct of the proposed architecture, we are able to explore the embedding space of the attributes extracted from different facial parts, such as mouth and eyes, to discover new attributes. Furthermore, through extensive experimentation, we show that the attribute features extracted by our method outperform the previously presented attribute-based method and a baseline LBP method for the task of active authentication. Lastly, we demonstrate the effectiveness of the proposed architecture in terms of speed and power consumption by deploying it on an actual mobile device.

show abstract

Attribute-based continuous user authentication on mobile devices

Cited by 47 publications

References 15 publications

Active user authentication for smartphones: A challenge data set and benchmark results

Active user authentication for smartphones: A challenge data set and benchmark results

Residual Codean Autoencoder for Facial Attribute Analysis

Convolutional neural networks for attribute-based active authentication on mobile devices

Contact Info

Product

Resources

About