Benchmarking Adversarially Robust Quantum Machine Learning at Scale

Abstract

Machine learning (ML) methods such as artificial neural networks are rapidly becoming ubiquitous in modern science, technology and industry. Despite their accuracy and sophistication, neural networks can be easily fooled by carefully designed malicious inputs known as adversarial attacks. While such vulnerabilities remain a serious challenge for classical neural networks, the extent of their existence is not fully understood in the quantum ML setting. In this work, we benchmark the robustness of quantum ML networks, such as quantum variational classifiers (QVC), at scale by performing rigorous training for both simple and complex image datasets and through a variety of high-end adversarial attacks. Our results show that QVCs offer a notably enhanced robustness against classical adversarial attacks by learning features which are not detected by the classical neural networks, indicating a possible quantum advantage for ML tasks. Contrarily, and remarkably, the converse is not true, with attacks on quantum networks also capable of deceiving classical neural networks. By combining quantum and classical network outcomes, we propose a novel adversarial attack detection technology. Traditionally quantum advantage in ML systems has been sought through increased accuracy or algorithmic speed-up, but our work has revealed the potential for a new kind of quantum advantage through superior robustness of ML models, whose practical realisation will address serious security concerns and reliability issues of ML algorithms employed in a myriad of applications including autonomous vehicles, cybersecurity, and surveillance robotic systems.

10 pages, 5 Figures

References in corpus (4)

• Quantum algorithm for solving linear systems of equations
• Challenges and Opportunities in Quantum Machine Learning
• Experimental quantum adversarial learning with programmable superconducting qubits
• Data compression for quantum machine learning

Cited by in corpus (20)

• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Towards quantum enhanced adversarial robustness in machine learning
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• Calibrating the role of entanglement in variational quantum circuits
• Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
• Training robust and generalizable quantum models
• Predominant Aspects on Security for Quantum Machine Learning: Literature Review
• Stabilizer Tensor Networks with Magic State Injection
• Boosted Ensembles of Qubit and Continuous Variable Quantum Support Vector Machines for B Meson Flavour Tagging
• Non-Unitary Quantum Machine Learning
• iQuantum: A Case for Modeling and Simulation of Quantum Computing Environments
• Designing Robust Quantum Neural Networks via Optimized Circuit Metrics
• Adversarial Robustness Guarantees for Quantum Classifiers
• Generating Universal Adversarial Perturbations for Quantum Classifiers
• Application-Oriented Benchmarking of Quantum Generative Learning Using QUARK
• Lean classical-quantum hybrid neural network model for image classification
• Almost fault-tolerant quantum machine learning with drastic overhead reduction
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning
• Classical Autoencoder Distillation of Quantum Adversarial Manipulations