Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise
Abstract
Recently, quantum classifiers have been found to be vulnerable to adversarial attacks, in which quantum classifiers are deceived by imperceptible noises, leading to misclassification. In this paper, we propose the first theoretical study demonstrating that adding quantum random rotation noise can improve robustness in quantum classifiers against adversarial attacks. We link the definition of differential privacy and show that the quantum classifier trained with the natural presence of additive noise is differentially private. Finally, we derive a certified robustness bound to enable quantum classifiers to defend against adversarial examples, supported by experimental results simulated with noises from IBM's 7-qubits device.
Cite
@article{arxiv.2211.00887,
title = {Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise},
author = {Jhih-Cing Huang and Yu-Lin Tsai and Chao-Han Huck Yang and Cheng-Fang Su and Chia-Mu Yu and Pin-Yu Chen and Sy-Yen Kuo},
journal= {arXiv preprint arXiv:2211.00887},
year = {2023}
}
Comments
Accepted to IEEE ICASSP 2023