Pith

open record

sign in

arxiv: 2211.00887 · v2 · pith:R7ALDONY · submitted 2022-11-02 · quant-ph · cs.LG· cs.NE· eess.SP

Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:R7ALDONYrecord.jsonopen to challenge →

classification quant-ph cs.LGcs.NEeess.SP
keywords quantumclassifiersadversarialnoiserobustnessattackscertifiedexamples
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.