Convolutional Neural Networks for Attribute-based Active Authentication on Mobile Devices
This work addresses the problem of resource-efficient active authentication for mobile device users, presenting an incremental improvement over existing attribute-based methods.
The authors tackled continuous authentication on mobile devices by proposing a multi-task, part-based deep convolutional neural network that learns intermediate features like gender and hair color, achieving better accuracy than state-of-the-art methods and demonstrating effectiveness in speed and power consumption on actual devices.
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.