Classical Autoencoder Distillation of Quantum Adversarial Manipulations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khatun, Amena, Usman, Muhammad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911308893388800
author Khatun, Amena
Usman, Muhammad
author_facet Khatun, Amena
Usman, Muhammad
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_09216
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Classical Autoencoder Distillation of Quantum Adversarial Manipulations
Khatun, Amena
Usman, Muhammad
Quantum Physics
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.
title Classical Autoencoder Distillation of Quantum Adversarial Manipulations
topic Quantum Physics
url https://arxiv.org/abs/2504.09216