Verifying Adversarial Robustness in Quantum Machine Learning: from theory to physical validation via a software tool

Abstract

As with classical neural networks, quantum machine learning (QML) models are vulnerable to small input perturbations that can significantly alter output predictions. Certifying the robustness of QML models, particularly on NISQ hardware, is therefore a fundamental step toward trustworthy quantum AI. This chapter reviews our recently developed comprehensive formal framework for verifying adversarial robustness in QML. The core of this framework is a fidelity-based robustness lower bound computable directly from the measurement outcome distribution, which enables both formal verification and empirical estimation on real quantum devices. Additionally, the optimal bound can be computed via semidefinite programming (SDP) with full knowledge of the quantum machine learning models. We incorporate these results into: (1) an efficient formal verification framework; (2) VeriQR, the first dedicated QML robustness verification tool; and (3) the first experimental benchmark of quantum adversarial robustness on a 20-qubit superconducting processor. Together, these systematic advances enable scalable, physically grounded robustness evaluation of QML models.

References in corpus (17)

• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Quantum Circuit Learning
• Evaluating analytic gradients on quantum hardware
• Challenges and Opportunities in Quantum Machine Learning
• Experimental Quantum Generative Adversarial Networks for Image Generation
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Quantum noise protects quantum classifiers against adversaries
• Quantum Adversarial Machine Learning
• Realizing Quantum Convolutional Neural Networks on a Superconducting Quantum Processor to Recognize Quantum Phases
• An Abstraction-Based Framework for Neural Network Verification
• Vulnerability of quantum classification to adversarial perturbations
• Realizing a quantum generative adversarial network using a programmable superconducting processor
• Robustness Verification of Quantum Classifiers
• Quantum Neuronal Sensing of Quantum Many-Body States on a 61-Qubit Programmable Superconducting Processor
• Predominant Aspects on Security for Quantum Machine Learning: Literature Review
• Detecting Violations of Differential Privacy for Quantum Algorithms