Experimental demonstration of adversarial examples in learning topological phases

TL;DR

This paper experimentally demonstrates that machine learning models for classifying topological phases of matter are vulnerable to adversarial examples, highlighting a critical reliability concern in applying AI to condensed matter physics.

Contribution

First experimental proof of adversarial examples in topological phase classification using a nitrogen-vacancy center platform.

Findings

Adversarial perturbations can deceive phase classifiers with over 99.2% accuracy on legitimate samples.

Demonstrates the vulnerability of machine learning in topological phase identification.

Provides guidance for future robust machine learning applications in condensed matter physics.

Abstract

Classification and identification of different phases and the transitions between them is a central task in condensed matter physics. Machine learning, which has achieved dramatic success in a wide range of applications, holds the promise to bring unprecedented perspectives for this challenging task. However, despite the exciting progress made along this direction, the reliability of machine-learning approaches likewise demands further investigation. Here, with the nitrogen-vacancy center platform, we report the first proof-of-principle experimental demonstration of adversarial examples in learning topological phases. We show that, after adding a tiny amount of carefully-designed perturbations, the experimentally observed adversarial examples can successfully deceive a splendid phase classifier, whose prediction accuracy is larger than $99.2\%$ on legitimate samples, with a notably high confidence. Our results explicitly showcase the crucial vulnerability aspect of applying machine learning techniques in classifying phases of matter, which provides an indispensable guide for future studies in this interdisciplinary field.