# Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier

## TL;DR

This paper introduces a CNN-based one-class classification method with autoencoder regularization for active authentication on mobile devices, demonstrating superior performance on face datasets by modeling genuine user data effectively.

## Contribution

It proposes a novel CNN approach using autoencoder regularization and Gaussian noise to improve one-class classification for active authentication, adaptable with any pre-trained CNN.

## Key findings

- Achieves superior accuracy compared to traditional methods.
- Effectively models genuine user data for continuous authentication.
- Demonstrates robustness across three face datasets.

## Abstract

Active authentication refers to the process in which users are unobtrusively monitored and authenticated continuously throughout their interactions with mobile devices. Generally, an active authentication problem is modelled as a one class classification problem due to the unavailability of data from the impostor users. Normally, the enrolled user is considered as the target class (genuine) and the unauthorized users are considered as unknown classes (impostor). We propose a convolutional neural network (CNN) based approach for one class classification in which a zero centered Gaussian noise and an autoencoder are used to model the pseudo-negative class and to regularize the network to learn meaningful feature representations for one class data, respectively. The overall network is trained using a combination of the cross-entropy and the reconstruction error losses. A key feature of the proposed approach is that any pre-trained CNN can be used as the base network for one class classification. Effectiveness of the proposed framework is demonstrated using three publically available face-based active authentication datasets and it is shown that the proposed method achieves superior performance compared to the traditional one class classification methods. The source code is available at: github.com/otkupjnoz/oc-acnn.