Classical autoencoder distillation of quantum adversarial manipulations

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 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 utilizing Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST (FMNIST) image datasets, and projected gradient descent and fast gradient sign method adversarial attack settings. Our work highlights a promising pathway to achieve fully robust quantum machine learning in both classical and quantum adversarial scenarios.