Neural Fuzzy Extractors: A Secure Way to Use Artificial Neural Networks for Biometric User Authentication

TL;DR

This paper introduces Neural Fuzzy Extractors, a novel architecture that securely combines neural networks with fuzzy extractors for biometric authentication, maintaining high performance while enhancing security against credential falsification.

Contribution

The paper presents the Neural Fuzzy Extractor (NFE), a new architecture that securely integrates neural classifiers with fuzzy extractors, minimizing performance loss and improving security in biometric authentication.

Findings

NFE can be retrofitted to existing neural networks with minimal performance impact.

The architecture enhances security by protecting user biometric data from falsification.

Demonstrated on fingerprint authentication with promising results.

Abstract

Powered by new advances in sensor development and artificial intelligence, the decreasing cost of computation, and the pervasiveness of handheld computation devices, biometric user authentication (and identification) is rapidly becoming ubiquitous. Modern approaches to biometric authentication, based on sophisticated machine learning techniques, cannot avoid storing either trained-classifier details or explicit user biometric data, thus exposing users' credentials to falsification. In this paper, we introduce a secure way to handle user-specific information involved with the use of vector-space classifiers or artificial neural networks for biometric authentication. Our proposed architecture, called a Neural Fuzzy Extractor (NFE), allows the coupling of pre-existing classifiers with fuzzy extractors, through a artificial-neural-network-based buffer called an expander, with minimal or no performance degradation. The NFE thus offers all the performance advantages of modern deep-learning-based classifiers, and all the security of standard fuzzy extractors. We demonstrate the NFE retrofit to a classic artificial neural network for a simple scenario of fingerprint-based user authentication.