Hardening Quantum Machine Learning Against Adversaries

by   Nathan Wiebe, et al.

Security for machine learning has begun to become a serious issue for present day applications. An important question remaining is whether emerging quantum technologies will help or hinder the security of machine learning. Here we discuss a number of ways that quantum information can be used to help make quantum classifiers more secure or private. In particular, we demonstrate a form of robust principal component analysis that, under some circumstances, can provide an exponential speedup relative to robust methods used at present. To demonstrate this approach we introduce a linear combinations of unitaries Hamiltonian simulation method that we show functions when given an imprecise Hamiltonian oracle, which may be of independent interest. We also introduce a new quantum approach for bagging and boosting that can use quantum superposition over the classifiers or splits of the training set to aggregate over many more models than would be possible classically. Finally, we provide a private form of k--means clustering that can be used to prevent an all powerful adversary from learning more than a small fraction of a bit from any user. These examples show the role that quantum technologies can play in the security of ML and vice versa. This illustrates that quantum computing can provide useful advantages to machine learning apart from speedups.


page 1

page 2

page 3

page 4


Quantum-inspired classical algorithms for principal component analysis and supervised clustering

We describe classical analogues to quantum algorithms for principal comp...

Quantum Speedup in Adaptive Boosting of Binary Classification

In classical machine learning, a set of weak classifiers can be adaptive...

Security Aspects of Quantum Machine Learning: Opportunities, Threats and Defenses

In the last few years, quantum computing has experienced a growth spurt....

New Trends in Quantum Machine Learning

Here we will give a perspective on new possible interplays between Machi...

Quantum noise protects quantum classifiers against adversaries

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

Considerations on Quantum-Based Methods for Communication Security

In this paper we provide an intuitive-level discussion of the challenges...

Boosting on the shoulders of giants in quantum device calibration

Traditional machine learning applications, such as optical character rec...

Please sign up or login with your details

Forgot password? Click here to reset