Convolutional Neural Networks for Attribute-based Active Authentication on Mobile Devices

TL;DR

This paper introduces a multi-task deep convolutional neural network for continuous, attribute-based authentication on mobile devices, achieving high accuracy with low resource consumption by focusing on facial attributes instead of identities.

Contribution

It proposes a novel multi-task, part-based DCNN architecture for facial attribute detection optimized for mobile devices, improving accuracy and efficiency over existing methods.

Findings

Outperforms state-of-the-art attribute detection methods in accuracy.

Demonstrates superior active authentication performance using attribute features.

Achieves real-time speed and low power consumption on mobile hardware.

Abstract

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, part-based 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.