Beyond Speech: Generalizing D-Vectors for Biometric Verification

Abstract

Deep learning based automatic feature extraction methods have radically transformed speaker identification and facial recognition. Current approaches are typically specialized for individual domains, such as Deep Vectors (D-Vectors) for speaker identification. We provide two distinct contributions: a generalized framework for biometric verification inspired by D-Vectors and novel models that outperform current stateof-the-art approaches. Our approach supports substitution of various feature extraction models and improves the robustness of verification tests across domains. We demonstrate the framework and models for two different behavioral biometric verification problems: keystroke and mobile gait. We present a comprehensive empirical analysis comparing our framework to the state-of-the-art in both domains. Our models perform verification with higher accuracy using orders of magnitude less data than state-of-the-art approaches in both domains. We believe that the combination of high accuracy and practical data requirements will enable application of behavioral biometric models outside of the laboratory in support of much-needed improvements to cyber security.

On the Inference of Soft Biometrics from Typing Patterns Collected in a Multi-device Environment

“…In addition to tuning the listed parameter, we also experimented with the number of features and presented the best results obtained. The encouraging performance of ML algorithms, as well as the size of data, motivated us to experiment with deep learning methods that have been effectively used for solving typing pattern-based identification and authentication, recently [Acien et al 2020;Baldwin et al 2019;Bernardi et al 2019;Sun et al 2017].…”

“…The combination of deep networks, along with the non-linear activation, has been influential in the popularity of deep learning algorithms. Recently, there have been several attempts at using deep learning architectures for analyzing keystroke biometric data [Acien et al 2020;Baldwin et al 2019;Bernardi et al 2019;Sun et al 2017]. Inspired by these approaches, we leverage the following deep learning models:…”

Authentication by Keystroke Dynamics: The Influence of Typing Language

“…They developed two free-text datasets, one using different keyboard types, and the other for bilingual English and Chinese speaking users. The bilingual dataset was collected using the user's personal keyboard, and was evaluated using two free-text algorithms, the ITAD metric [8] and D-Vectors model [9]. They reported that the use of different languages significantly affected the keystroke dynamics system's performance, with an average EER of 0.210% when enrolling in English and testing on Chinese, and 0.253% when enrolling in Chinese and testing on English.…”

Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining

“…However, in any classification task such as identification of rare objects (unique species of birds) [1], diagnosing uncommon diseases [2], authenticating a new employee in large enterprise (i.e. speech biometry) [3], detection of rare acoustic events (e.g. in audio surveillance) [4][5][6], it is a challenge to create generalizable models using traditional deep neural networks.…”