VerIde ECG Biometrics: Verification and Identification

TL;DR

This study addresses large-scale ECG biometrics and privacy risks by comparing fiducial-feature representations with full-waveform embeddings learned via Siamese and ArcFace architectures. It demonstrates that identity signals exist in tabular ECG features and are amplified when learning embeddings from waveforms; on a dataset with about $2.3\times 10^4$ identities and roughly $5.6\times 10^4$ ECGs, tasks reach $TAR=0.908$ at $FAR=10^{-3}$ and $TAR=0.820$ at $FAR=10^{-4}$ with an all-vs-all $EER=2.53\%$, while open-set DIR@FAR reaches up to $0.976$ in two-stage pipelines. The results support a persistent individual ECG signature across sessions, prompting discussion of privacy protections and deployment protocols. The work emphasizes operational biometrics metrics (DIR@FAR, TAR@FAR, Rank@K) and provides a reproducible pipeline for large-scale ECG verification and identification.

Abstract

This work studies electrocardiogram (ECG) biometrics at large scale, evaluating how strongly an ECG can be linked to an individual and, consequently, how its anonymization may be compromised. We show that identity information is already present in tabular representations (fiducial features): even a simple MLP-based embedding network yields non-trivial performance, indicating that anonymization based solely on releasing features does not guarantee privacy. We then adopt embedding-based deep learning models (ArcFace), first on features and then on ECG waveforms, showing a performance jump when moving from tabular inputs to waveforms, and a further gain with larger training sets and consistent normalization across train/val/test. On a large-scale test set, verification achieves high TAR at strict FAR thresholds (TAR=0.908 @ FAR=1e-3; TAR=0.820 @ FAR=1e-4) with EER=2.53% (all-vs-all); closed-set identification yields Rank@1=0.812 and Rank@10=0.910. In open-set, a two-stage pipeline (top-K shortlist on embeddings + re-ranking) reaches DIR@FAR up to 0.976 at FAR=1e-3 and 1e-4. Overall, the results show that ECG carries a measurable individual signature: re-identification is already possible with tabular features and is further amplified by embedding-based models, making privacy implications and realistic operational protocols essential to consider.