Gait-Based Continuous Authentication Using Multimodal Learning

The ever-growing threats of security and privacy loss from unauthorized access to mobile devices has led to the development of various biometric authentication methods for easier and safer data access. In this work we present a gait-based continuous authentication method using accelerometer and ground contact force data recorded from a pair of smart socks. Multi-modal learning and auto-encoders are used for feature extraction and a multi-task learning approach is used for classification. The effectiveness of the proposed approach has been demonstrated through preliminary experiments on a dataset of 8 subjects.