VeriQR - A Robustness Verification Tool for Quantum Machine Learning Models - Early Version

Aug 3, 2026

Upload by Violet

Adversarial noise attacks pose a serious threat to quantum machine learning (QML) models, especially in the Noisy Intermediate-Scale Quantum (NISQ) era where noise is unavoidable. VeriQR is introduced as a formal verification tool tailored to QML robustness, simulating real hardware noise by injecting random noise. It offers sound and complete algorithms for both local and global robustness, including an under-approximate approach and a tensor-network method. The tool detects adversarial examples, supports adversarial training to improve local robustness, and allows customized noise, with experiments on real-world QML models and a user-friendly graphical interface.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Abstract

Keywords

1 Introduction

Edinburgh Research Explorer VeriQR A robustness verification tool for quantum machine learning models Citation for published version: Lin, Y, Guan, J, Fang, W, Ying, M & Su, Z 2024 'VeriQR: A robustness verification tool for quantum machine learning models' ArXiv, pp. 1-18. [https://doi.org/10.48550/arXiv.2407.13533](https://doi.org/10.48550/arXiv.2407.13533) Digital Object Identifier (DOI): 10.48550/arXiv.2407.13533 Link: Link to publication record in Edinburgh Research Explorer Document Version: Early version, also known as pre-print General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer content complies with UK legislation. If you believe that the public display of this file breaches copyright please [contact openaccess@ed.ac.uk](contact openaccess@ed.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim. Download date: 03. Oct. 2024 VeriQR: A Robustness Verification Tool for Quantum Machine Learning Models Yanling Lin 1 ,2 , Ji Guan2 (B) ⋆ , Wang Fang2 , Mingsheng Ying3 , Zhaofeng Su 1 (B) ⋆⋆ arXiv :2407 . 13533v1 [ quant-ph] 18 Jul 2024 1 2 University of Science and Technology of China, Hefei 230026, China Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing 100190, China 3 Centre for Quantum Software and Information, University of Technology Sydney, NSW 2007, Australia Abstract. Adversarial noise attacks present a significant threat to quantum machine learning (QML) models, similar to their classical counterparts. This is especially true in the current Noisy Intermediate-Scale Quantum era, where noise is unavoidable. Therefore, it is essential to ensure the robustness of QML models before their deployment. To address this challenge, we introduce VeriQR, the first tool designed specifically for formally verifying and improving the robustness of QML models, to the best of our knowledge. This tool mimics real-world quantum hardware’s noisy impacts by incorporating random noise to formally validate a QML model’s robustness. VeriQR supports exact (sound and complete) algorithms for both local and global robustness verification. For enhanced efficiency, it implements an under-approximate (complete) algorithm and a tensor network-based algorithm to verify local and global robustness, respectively. As a formal verification tool, VeriQR can detect adversarial examples and utilize them for further analysis and to enhance the local robustness through adversarial training, as demonstrated by experiments on real-world quantum machine learning models. Moreover, it permits users to incorporate customized noise. Based on this feature, we assess VeriQR using various real-world examples, and experimental outcomes confirm that the addition of specific quantum noise can enhance the global robustness of QML models. These processes are made accessible through a user-friendly graphical interface provided by VeriQR, catering to general users without requiring a deep understanding of the counter-intuitive probabilistic nature of quantum computing. The source code of VeriQR is available at [https://github.com/Veri-Q/](https://github.com/Veri-Q/)[ ](https://github.com/Veri-Q/)VeriQR, while the artifact for reproducing the experiments of this paper is available at [29] . Keywords: Robustness Verification · Quantum Machine Learning · Formal Verification ·Quantum Classifiers · Quantum Noise ⋆ ⋆⋆ [guanj@ios.ac.cn](guanj@ios.ac.cn)[ ](guanj@ios.ac.cn)[zfsu@ustc.edu.cn](z

FAQs

What problem does VeriQR address for quantum machine learning models?

VeriQR addresses the threat of adversarial noise attacks to QML models, which is especially critical in the NISQ era where noise cannot be avoided.

How does VeriQR model the noise affecting quantum hardware?

VeriQR mimics real-world quantum hardware impacts by incorporating random noise to formally validate a QML model’s robustness.

What robustness checks does VeriQR support?

VeriQR supports both local and global robustness verification with sound and complete algorithms, using an under-approximate method for local robustness and a tensor-network-based method for global robustness.

Aug 3, 2026

Upload by Violet