Quantum noise protects quantum classifiers against adversaries

by   Yuxuan Du, et al.

Noise in quantum information processing is often viewed as a disruptive and difficult-to-avoid feature, especially in near-term quantum technologies. However, noise has often played beneficial roles, from enhancing weak signals in stochastic resonance to protecting the privacy of data in differential privacy. It is then natural to ask, can we harness the power of quantum noise that is beneficial to quantum computing? An important current direction for quantum computing is its application to machine learning, such as classification problems. One outstanding problem in machine learning for classification is its sensitivity to adversarial examples. These are small, undetectable perturbations from the original data where the perturbed data is completely misclassified in otherwise extremely accurate classifiers. They can also be considered as `worst-case' perturbations by unknown noise sources. We show that by taking advantage of depolarisation noise in quantum circuits for classification, a robustness bound against adversaries can be derived where the robustness improves with increasing noise. This robustness property is intimately connected with an important security concept called differential privacy which can be extended to quantum differential privacy. For the protection of quantum data, this is the first quantum protocol that can be used against the most general adversaries. Furthermore, we show how the robustness in the classical case can be sensitive to the details of the classification model, but in the quantum case the details of classification model are absent, thus also providing a potential quantum advantage for classical data that is independent of quantum speedups. This opens the opportunity to explore other ways in which quantum noise can be used in our favour, as well as identifying other ways quantum algorithms can be helpful that is independent of quantum speedups.


page 1

page 2

page 3

page 4


Quantum Differential Privacy: An Information Theory Perspective

Differential privacy has been an exceptionally successful concept when i...

Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise

Recently, quantum classifiers have been known to be vulnerable to advers...

Differential Privacy Amplification in Quantum and Quantum-inspired Algorithms

Differential privacy provides a theoretical framework for processing a d...

Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testing

Quantum machine learning models have the potential to offer speedups and...

Enhancing Quantum Adversarial Robustness by Randomized Encodings

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

Hardening Quantum Machine Learning Against Adversaries

Security for machine learning has begun to become a serious issue for pr...

Quantum Private Distributed Learning Through Blind Quantum Computing

Private distributed learning studies the problem of how multiple distrib...

Please sign up or login with your details

Forgot password? Click here to reset