QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems

Abstract

Quantum Neural Network (QNN) combines the Deep Learning (DL) principle with the fundamental theory of quantum mechanics to achieve machine learning tasks with quantum acceleration. Recently, QNN systems have been found to manifest robustness issues similar to classical DL systems. There is an urgent need for ways to test their correctness and security. However, QNN systems differ significantly from traditional quantum software and classical DL systems, posing critical challenges for QNN testing. These challenges include the inapplicability of traditional quantum software testing methods to QNN systems due to differences in programming paradigms and decision logic representations, the dependence of quantum test sample generation on perturbation operators, and the absence of effective information in quantum neurons. In this paper, we propose QuanTest, a quantum entanglement-guided adversarial testing framework to uncover potential erroneous behaviors in QNN systems. We design a quantum entanglement adequacy criterion to quantify the entanglement acquired by the input quantum states from the QNN system, along with two similarity metrics to measure the proximity of generated quantum adversarial examples to the original inputs. Subsequently, QuanTest formulates the problem of generating test inputs that maximize the quantum entanglement adequacy and capture incorrect behaviors of the QNN system as a joint optimization problem and solves it in a gradient-based manner to generate quantum adversarial examples. results demonstrate that QuanTest possesses the capability to capture erroneous behaviors in QNN systems. The entanglement-guided approach proves effective in adversarial testing, generating more adversarial examples.

This paper has been accepted by TOSEM 2024

References in corpus (12)

• Quantum algorithm for solving linear systems of equations
• Suppressing quantum errors by scaling a surface code logical qubit
• Quantum circuits with many photons on a programmable nanophotonic chip
• Quantum advantage in learning from experiments
• Quantum convolutional neural network for classical data classification
• Statistical Assertions for Validating Patterns and Finding Bugs in Quantum Programs
• Experimental quantum adversarial learning with programmable superconducting qubits
• Scalable measures of magic resource for quantum computers
• On Testing Quantum Programs
• Optimal measurements for quantum fidelity between Gaussian states and its relevance to quantum metrology
• Universal Adversarial Examples and Perturbations for Quantum Classifiers
• Generating Universal Adversarial Perturbations for Quantum Classifiers