Detecting Violations of Differential Privacy for Quantum Algorithms

TL;DR

This paper introduces a formal framework and an efficient detection algorithm to identify violations of differential privacy in quantum algorithms, utilizing Tensor Networks and tested on various quantum computing platforms.

Contribution

It presents the first formal method for detecting privacy violations in quantum algorithms, with an implementation that verifies privacy across multiple quantum computing models.

Findings

Effective detection of privacy violations in quantum algorithms.

Algorithm verified on real quantum computers with up to 21 qubits.

Applicable to diverse quantum algorithms including quantum supremacy and machine learning.

Abstract

Quantum algorithms for solving a wide range of practical problems have been proposed in the last ten years, such as data search and analysis, product recommendation, and credit scoring. The concern about privacy and other ethical issues in quantum computing naturally rises up. In this paper, we define a formal framework for detecting violations of differential privacy for quantum algorithms. A detection algorithm is developed to verify whether a (noisy) quantum algorithm is differentially private and automatically generate bugging information when the violation of differential privacy is reported. The information consists of a pair of quantum states that violate the privacy, to illustrate the cause of the violation. Our algorithm is equipped with Tensor Networks, a highly efficient data structure, and executed both on TensorFlow Quantum and TorchQuantum which are the quantum extensions of famous machine learning platforms -- TensorFlow and PyTorch, respectively. The effectiveness and efficiency of our algorithm are confirmed by the experimental results of almost all types of quantum algorithms already implemented on realistic quantum computers, including quantum supremacy algorithms (beyond the capability of classical algorithms), quantum machine learning models, quantum approximate optimization algorithms, and variational quantum eigensolvers with up to 21 quantum bits.