# Continuous Authentication of Wearable Device Users from Heart Rate, Gait, and Breathing Data

arXiv: https://arxiv.org/abs/2008.10779 · HTML: https://mlsanity.com/paper/2008.10779/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2020.

## Built on by (most cited first, 5 of 5)

- [Transfer Learning to Detect COVID-19 Coughs with Incremental Addition of Patient Coughs to Healthy People's Cough Detection Models](https://mlsanity.com/paper/2311.06707/) (2023)
- [Opportunistic Multi-Modal User Authentication for Health-Tracking IoT Wearables](https://mlsanity.com/paper/2109.13705/) (2021)
- [Cough Classification using Few-Shot Learning](https://mlsanity.com/paper/2509.09515/) (2025)
- [Sound Classification of Four Insect Classes](https://mlsanity.com/paper/2412.12395/) (2024)
- [A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains](https://mlsanity.com/paper/2504.04017/) (2025)

## Abstract (arXiv)

The security of private information is becoming the bedrock of an increasingly digitized society. While the users are flooded with passwords and PINs, these gold-standard explicit authentications are becoming less popular and valuable. Recent biometric-based authentication methods, such as facial or finger recognition, are getting popular due to their higher accuracy. However, these hard-biometric-based systems require dedicated devices with powerful sensors and authentication models, which are often limited to most of the market wearables. Still, market wearables are collecting various private information of a user and are becoming an integral part of life: accessing cars, bank accounts, etc. Therefore, time demands a burden-free implicit authentication mechanism for wearables using the less-informative soft-biometric data that are easily obtainable from modern market wearables. In this work, we present a context-dependent soft-biometric-based authentication system for wearables devices using heart rate, gait, and breathing audio signals. From our detailed analysis using the "leave-one-out" validation, we find that a lighter k-Nearest Neighbor (k-NN) model with k = 2 can obtain an average accuracy of 0.93 ± 0.06, F1 score 0.93 ± 0.03, and em false positive rate (FPR) below 0.08 at 50% level of confidence, which shows the promise of this work.