Blind quantum machine learning

TL;DR

This paper introduces the first blind quantum machine learning protocol allowing a classical client to securely classify vectors using a remote quantum processor, preserving data privacy and detecting eavesdroppers.

Contribution

It presents a novel BQML protocol enabling privacy-preserving classification with minimal client quantum operations and security against interception.

Findings

Protocol securely classifies 2D vectors

Client only needs to rotate and measure a single qubit

Eavesdroppers can be detected during the process

Abstract

Blind quantum machine learning (BQML) enables a classical client with little quantum technology to delegate a remote quantum machine learning to the quantum server in such a approach that the privacy data is preserved. Here we propose the first BQML protocol that the client can classify two-dimensional vectors to different clusters, resorting to a remote small-scale photon quantum computation processor. During the protocol, the client is only required to rotate and measure the single qubit. The protocol is secure without leaking any relevant information to the Eve. Any eavesdropper who attempts to intercept and disturb the learning process can be noticed. In principle, this protocol can be used to classify high dimensional vectors and may provide a new viewpoint and application for quantum machine learning.