EarPass: Unlock When Wearing Your Earphones

With the growing reliance on digital systems in today's mobile Internet era, robust authentication methods are crucial for safeguarding personal data and controlling access to resources. Conventional methods, such as knowledge-based and biometric-based authentication, are widely used but still have some usage limitations and potential security concerns, like wearing protective suits/masks or being imitated by attackers with ulterior motives. In this paper, we propose another earphone-based authentication system, namely EarPass, that leverages users' unique head motion patterns in response to a very short period of music segment. Here, we employ a Convolutional Neural Network (CNN)-based feature extractor to capture and map distinct head motions into a well-separated latent space, achieving high-dimensional data extraction. We demonstrate the consistency, uniqueness, and robustness of head motion patterns through extensive experiments and reach a 98.2% F1-score, indicating superior performance compared to conventional authentication methods. Additionally, EarPass is user-friendly, secure, and adaptable to various environments, including noisy and movement-oriented scenarios. By integrating the authentication system into Android devices, we showcase its real-world applicability and low energy consumption with minimal latency. The source code of EarPass will be open-source to further research and collaboration within the community.

I. Introduction

With the increasing reliance on digital systems in our daily lives, authentication methods have become essential for protecting our personal data, controlling access to resources, preventing identity theft, and complying with regulations [1]. It constructs a solid layer that verifies the identity of users and restricts access to specific individuals or groups [2]. Conventionally, authentication methods can be broadly categorized into knowledge-based authentication methods (e.g., passwords and graphical locks) and biometric-based authentication methods (e.g., fingerprints and facial recognition) [3]. However, such methods exhibit certain shortcomings. For example, passwords might be captured during the user's input through a recording attack, and shoulder-surfing attack [4]. Similarly, biometric data could be imitated through video recording [5]. On the other hand, the growing prevalence of smart wearable devices offers alternative approaches to user authentication like smartwatch [6] and virtual reality device [7]. Nevertheless, it requires extra effort from users to perform large-scale gestures [8] and is still susceptible to recording attacks [9].