Experimental demonstration of adversarial examples in learning topological phases

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.

References in corpus (50)

• Classification of topological insulators and superconductors in three spatial dimensions
• Quantum Simulation
• The nitrogen-vacancy colour centre in diamond
• Experimental loophole-free violation of a Bell inequality using entangled electron spins separated by 1.3 km
• Machine learning and the physical sciences
• On the Measurement of Qubits
• Periodic table for topological insulators and superconductors
• One pixel attack for fooling deep neural networks
• Machine learning phases of matter
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Chern Numbers in Discretized Brillouin Zone: Efficient Method of Computing (Spin) Hall Conductances
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Sensitivity Optimization for NV-Diamond Magnetometry
• Solid-state electronic spin coherence time approaching one second
• Learning phase transitions by confusion
• Realization of a multi-node quantum network of remote solid-state qubits
• Discovering Phase Transitions with Unsupervised Learning
• Deterministic delivery of remote entanglement on a quantum network
• Nanoscale magnetic imaging of a single electron spin under ambient conditions
• Dynamic polarization of single nuclear spins by optical pumping of NV color centers in diamond at room temperature
• Entanglement Distillation between Solid-State Quantum Network Nodes
• Decoherence-protected quantum gates for a hybrid solid-state spin register
• Anisotropic interactions of a single spin and dark-spin spectroscopy in diamond
• Machine learning quantum phases of matter beyond the fermion sign problem
• Identifying topological order through unsupervised machine learning
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• Scalable Architecture for a Room Temperature Solid-State Quantum Information Processor
• Imaging stress and magnetism at high pressures using a nanoscale quantum sensor
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Topological surface states in three-dimensional magnetic insulators
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Unsupervised machine learning and band topology
• Machine learning meets quantum physics
• Machine Learning ${\mathbb{Z}}_2$ Quantum Spin Liquids with Quasi-particle Statistics
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Unsupervised Manifold Clustering of Topological Phononics
• Observation of non-Hermitian topology with non-unitary dynamics of solid-state spins
• Hopf Insulators and Their Topologically Protected Surface States
• Unsupervised machine learning of topological phase transitions from experimental data
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Efficient Implementation of a Quantum Algorithm in a Single Nitrogen Vacancy Center of Diamond
• Unsupervised machine learning of quantum phase transitions using diffusion maps
• Probing quantum thermalization of a disordered dipolar spin ensemble with discrete time-crystalline order
• Unsupervised Learning of Non-Hermitian Topological Phases
• Direct Probe of Topological Order for Cold Atoms
• Experimental Adiabatic Quantum Factorization under Ambient Conditions Based on a Solid-State Single Spin System
• Observation of topological links associated with Hopf insulators in a solid-state quantum simulator
• A supervised learning algorithm for interacting topological insulators based on local curvature
• A learning algorithm with emergent scaling behavior for classifying phase transitions

Cited by in corpus (5)

• Identifying topology of leaky photonic lattices with machine learning
• A simple framework for contrastive learning phases of matter
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Quantum Inception Score
• Artificial intelligence for representing and characterizing quantum systems