Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise

by   Jhih-Cing Huang, et al.

Recently, quantum classifiers have been known to be vulnerable to adversarial attacks, where quantum classifiers are fooled by imperceptible noises to have misclassification. In this paper, we propose one first theoretical study that utilizing the added quantum random rotation noise can improve the robustness of quantum classifiers against adversarial attacks. We connect the definition of differential privacy and demonstrate the quantum classifier trained with the natural presence of additive noise is differentially private. Lastly, we derive a certified robustness bound to enable quantum classifiers to defend against adversarial examples supported by experimental results.


page 1

page 2

page 3

page 4


A unifying framework for differentially private quantum algorithms

Differential privacy is a widely used notion of security that enables th...

Enhancing Quantum Adversarial Robustness by Randomized Encodings

The interplay between quantum physics and machine learning gives rise to...

Quantum noise protects quantum classifiers against adversaries

Noise in quantum information processing is often viewed as a disruptive ...

Towards quantum enhanced adversarial robustness in machine learning

Machine learning algorithms are powerful tools for data driven tasks suc...

CycleGAN: a Master of Steganography

CycleGAN is one of the latest successful approaches to learn a correspon...

Adversarial Attacks and Defences Competition

To accelerate research on adversarial examples and robustness of machine...

Adversarial Examples Are a Natural Consequence of Test Error in Noise

Over the last few years, the phenomenon of adversarial examples --- mali...

Please sign up or login with your details

Forgot password? Click here to reset