Experimental quantum adversarial learning with programmable superconducting qubits

Abstract

Quantum computing promises to enhance machine learning and artificial intelligence. Different quantum algorithms have been proposed to improve a wide spectrum of machine learning tasks. Yet, recent theoretical works show that, similar to traditional classifiers based on deep classical neural networks, quantum classifiers would suffer from the vulnerability problem: adding tiny carefully-crafted perturbations to the legitimate original data samples would facilitate incorrect predictions at a notably high confidence level. This will pose serious problems for future quantum machine learning applications in safety and security-critical scenarios. Here, we report the first experimental demonstration of quantum adversarial learning with programmable superconducting qubits. We train quantum classifiers, which are built upon variational quantum circuits consisting of ten transmon qubits featuring average lifetimes of 150 $\mu$s, and average fidelities of simultaneous single- and two-qubit gates above 99.94% and 99.4% respectively, with both real-life images (e.g., medical magnetic resonance imaging scans) and quantum data. We demonstrate that these well-trained classifiers (with testing accuracy up to 99%) can be practically deceived by small adversarial perturbations, whereas an adversarial training process would significantly enhance their robustness to such perturbations. Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.

arXiv comment26 pages, 17 figures, 8 algorithms

References in corpus (19)

• Quantum Machine Learning
• Supervised learning with quantum enhanced feature spaces
• Quantum Circuit Learning
• Evaluating analytic gradients on quantum hardware
• Data re-uploading for a universal quantum classifier
• New material platform for superconducting transmon qubits with coherence times exceeding 0.3 milliseconds
• Quantum advantage in learning from experiments
• A rigorous and robust quantum speed-up in supervised machine learning
• Demonstrating a Continuous Set of Two-qubit Gates for Near-term Quantum Algorithms
• Hybrid Quantum-Classical Approach to Quantum Optimal Control
• Experimental quantum speed-up in reinforcement learning agents
• Machine learning meets quantum physics
• Quantum Adversarial Machine Learning
• Realizing Quantum Convolutional Neural Networks on a Superconducting Quantum Processor to Recognize Quantum Phases
• Recent advances for quantum classifiers
• Vulnerability of quantum classification to adversarial perturbations
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Robustness Verification of Quantum Classifiers
• Universal Adversarial Examples and Perturbations for Quantum Classifiers

Cited by in corpus (34)

• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• Towards quantum enhanced adversarial robustness in machine learning
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Deep quantum neural networks equipped with backpropagation on a superconducting processor
• Quantum Neuronal Sensing of Quantum Many-Body States on a 61-Qubit Programmable Superconducting Processor
• Quantum Capsule Networks
• Simulating unsteady fluid flows on a superconducting quantum processor
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
• Enabling Large-Scale and High-Precision Fluid Simulations on Near-Term Quantum Computers
• Training robust and generalizable quantum models
• Control and mitigation of microwave crosstalk effect with superconducting qubits
• Predominant Aspects on Security for Quantum Machine Learning: Literature Review
• Tunable Coupling Architectures with Capacitively Connecting Pads for Large-Scale Superconducting Multi-Qubit Processors
• Ensemble-learning error mitigation for variational quantum shallow-circuit classifiers
• Statistical Complexity of Quantum Learning
• High-precision pulse calibration of tunable couplers for high-fidelity two-qubit gates in superconducting quantum processors
• Hybrid quantum learning with data re-uploading on a small-scale superconducting quantum simulator
• Control the qubit-qubit coupling in the superconducting circuit with double-resonator couplers
• Digital-analog quantum learning on Rydberg atom arrays
• Quantum continual learning on a programmable superconducting processor
• Adversarial Robustness Guarantees for Quantum Classifiers
• QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
• Generating Universal Adversarial Perturbations for Quantum Classifiers
• Tunable compact on-chip superconducting switch
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Exploring nontrivial topology at quantum criticality in a superconducting processor
• Probing many-body Bell correlation depth with superconducting qubits
• Quantum Machine Learning of Molecular Energies with Hybrid Quantum-Neural Wavefunction
• Quantum Reservoir Computing for Realized Volatility Forecasting
• Magnon squeezing near a quantum critical point in a cavity-magnon-qubit system
• Application a quantum machine learning algorithm to the applied problem of modeling the thermal regime of a servers
• Classical Autoencoder Distillation of Quantum Adversarial Manipulations
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning