Classical Autoencoder Distillation of Quantum Adversarial Manipulations

Abstract

Quantum neural networks have been proven robust against classical adversarial attacks, but their vulnerability against quantum adversarial attacks is still a challenging problem. Here we report a new technique for the distillation of quantum manipulated image datasets by using classical autoencoders. Our technique recovers quantum classifier accuracies when tested under standard machine learning benchmarks utilising MNIST and FMNIST image datasets, and PGD and FGSM adversarial attack settings. Our work highlights a promising pathway to achieve fully robust quantum machine learning in both classical and quantum adversarial scenarios.

References in corpus (11)

• Quantum Convolutional Neural Networks
• How I failed machine learning in medical imaging -- shortcomings and recommendations
• Quantum noise protects quantum classifiers against adversaries
• Quantum Adversarial Machine Learning
• Experimental quantum adversarial learning with programmable superconducting qubits
• Vulnerability of quantum classification to adversarial perturbations
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Experimental exploration of five-qubit quantum error correcting code with superconducting qubits
• 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
• Non-Unitary Quantum Machine Learning