PPG as a Bridge: Cross-Device Authentication for Smart Wearables with Photoplethysmography

TL;DR

PPGTransID tackles the challenge of authenticating lightweight wearables without per-device enrollment by leveraging cross-device physiological consistency between a smartphone's remote PPG (rPPG) extracted from facial video and wearable PPG signals. The approach deploys a three-component system (wearables, a token smartphone with FaceID/Fingerprint-like capability, and a CDA process) and a unified preprocessing and feature-extraction pipeline, using multiple rPPG extraction methods and a suite of 21 pairwise features fed to classifiers (with XGBoost as the default). Across three user studies, PPGTransID achieves high authentication performance (BAC around 95–98%), robust generalization to unseen devices and postures, and resilience to replay attacks, while remaining unobtrusive and usable in real-world scenarios, including real-time demonstrations on a phone and a laptop. The results suggest that PPG-based cross-device authentication can extend strong, device-specific security to a broad wearable ecosystem, enabling seamless, privacy-conscious, and scalable access control in daily life. Limitations include signal duration requirements, motion sensitivity, and privacy considerations, with future work focusing on improved denoising, larger datasets, and continuous authentication to strengthen security without compromising usability.

Abstract

As smart wearable devices become increasingly powerful and pervasive, protecting user privacy on these devices has emerged as a critical challenge. While existing authentication mechanisms are available for interaction-rich devices such as smartwatches, enabling on-device authentication (ODA) on interaction-limited wearables including rings, earphones, glasses, and wristbands remains difficult. Moreover, as users increasingly own multiple smart devices, relying on device-specific authentication methods becomes redundant and burdensome. To address these challenges, we present PPGTransID, a ubiquitous and unobtrusive cross-device authentication (CDA) approach that leverages the real-time physiological consistency of photoplethysmography (PPG) signals across the human body. PPGTransID utilizes widely available PPG sensors on wearable devices to capture users' physiological signals and compares them with remote PPG (rPPG) signals extracted from a smartphone camera, where robust face-based authentication is already established. In doing so, PPGTransID securely transfers the reliable authentication status of the smartphone to nearby wearable devices without requiring additional user interaction. An evaluation with 33 participants shows that PPGTransID achieves a balanced accuracy of 95.5 percent and generalizes across multiple wearable form factors. Robustness experiments with 10 participants demonstrate resilience to variations in lighting, camera placement, and user behavior, while a real-time usability study with 14 participants confirms reliable performance with minimal interaction burden.

Figures (14)

• Figure 1: Demonstration of Hardware Devices. Illustration of device wearable placement and usage (left) and close-up views of the hardware used in our studies (right).
• Figure 2: Preprocessing Pipeline. To normalize PPG signals across devices and sensing modalities, signals are resampled, filtered, and detrended. For multi-channel devices, a quality score is computed for each channel, and the best channel is selected. MA processing classifies signals as clean, weakly corrupted, or heavily corrupted; heavily corrupted signals are discarded, while weakly corrupted signals are mitigated using a specialized moving average filter. Pairwise features are then extracted from the cleaned PPG pairs.
• Figure 3: t-SNE Visualization of Features. Features from 5 random subjects before classifier implementation. (a) Blue: signals synchronously collected on different devices from the same subject. Red: signals from different subjects on different devices. (b) Blue: same as (a). Red: pairs from the same subject but with a 60s temporal offset.
• Figure 4: Devices and Experimental Setup in Study 1. Illustration of the experimental setup in Study 1, showing the wearing placements, device arrangements, and the platforms used on the smartphones and laptop.
• Figure 5: Trade-off among Model Performance, Latency, and Size. The y-axis shows mean BAC, the x-axis shows inference latency, and bubble size represents model size (number of parameters). XGBoost offered the best balance of accuracy, compactness, and speed.