Portable Trust: biometric-based authentication and blockchain storage for self-sovereign identity systems

TL;DR

This paper presents a fully local, biometric-based authentication system on smartphones that captures, processes, and matches fingerprints without cloud reliance, supporting self-sovereign identity with blockchain integration.

Contribution

It introduces a novel mobile fingerprint authentication method using only built-in hardware and local processing, suitable for offline and remote scenarios.

Findings

Achieved 55% mean matching accuracy

Highest accuracy of 67% on thumb fingerprints

Demonstrated rapid fingerprint capture in seconds

Abstract

We devised a mobile biometric-based authentication system only relying on local processing. Our Android open source solution explores the capability of current smartphones to acquire, process and match fingerprints using only its built-in hardware. Our architecture is specifically designed to run completely locally and autonomously, not requiring any cloud service, server, or permissioned access to fingerprint reader hardware. It involves three main stages, starting with the fingerprint acquisition using the smartphone camera, followed by a processing pipeline to obtain minutiae features and a final step for matching against other locally stored fingerprints, based on Oriented FAST and Rotated BRIEF (ORB) descriptors. We obtained a mean matching accuracy of 55%, with the highest value of 67% for thumb fingers. Our ability to capture and process a finger fingerprint in mere seconds using a smartphone makes this work usable in a wide range of scenarios, for instance, offline remote regions. This work is specifically designed to be a key building block for a self-sovereign identity solution and integrate with our permissionless blockchain for identity and key attestation.