VeriQR: A Robustness Verification Tool for Quantum Machine Learning Models

TL;DR

VeriQR is a novel formal verification tool designed to assess and improve the robustness of quantum machine learning models against adversarial noise, incorporating real-world quantum noise effects and providing user-friendly interfaces.

Contribution

It introduces the first dedicated tool for formal robustness verification of QML models, supporting exact and approximate algorithms, and demonstrates noise-based robustness enhancement.

Findings

VeriQR effectively detects adversarial examples in QML models.

Adding specific quantum noise can improve global robustness.

The tool is accessible via a user-friendly graphical interface.

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 \textit{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. \textit{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, \textit{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 \textit{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 \textit{VeriQR}, catering to general users without requiring a deep understanding of the counter-intuitive probabilistic nature of quantum computing.