Quantum Adversarial Machine Learning

Abstract

Adversarial machine learning is an emerging field that focuses on studying vulnerabilities of machine learning approaches in adversarial settings and developing techniques accordingly to make learning robust to adversarial manipulations. It plays a vital role in various machine learning applications and has attracted tremendous attention across different communities recently. In this paper, we explore different adversarial scenarios in the context of quantum machine learning. We find that, similar to traditional classifiers based on classical neural networks, quantum learning systems are likewise vulnerable to crafted adversarial examples, independent of whether the input data is classical or quantum. In particular, we find that a quantum classifier that achieves nearly the state-of-the-art accuracy can be conclusively deceived by adversarial examples obtained via adding imperceptible perturbations to the original legitimate samples. This is explicitly demonstrated with quantum adversarial learning in different scenarios, including classifying real-life images (e.g., handwritten digit images in the dataset MNIST), learning phases of matter (such as, ferromagnetic/paramagnetic orders and symmetry protected topological phases), and classifying quantum data. Furthermore, we show that based on the information of the adversarial examples at hand, practical defense strategies can be designed to fight against a number of different attacks. Our results uncover the notable vulnerability of quantum machine learning systems to adversarial perturbations, which not only reveals a novel perspective in bridging machine learning and quantum physics in theory but also provides valuable guidance for practical applications of quantum classifiers based on both near-term and future quantum technologies.

arXiv comment22 pages, 16 figures, 5 tables

References in corpus (77)

• Quantum Computing in the NISQ era and beyond
• Quantum Machine Learning
• Quantum algorithm for solving linear systems of equations
• Hardware-efficient Variational Quantum Eigensolver for Small Molecules and Quantum Magnets
• Supervised learning with quantum enhanced feature spaces
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Experimental realisation of the topological Haldane model
• A Quantum Engineer's Guide to Superconducting Qubits
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• Machine learning phases of matter
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Quantum principal component analysis
• Trapped-Ion Quantum Computing: Progress and Challenges
• Circuit-centric quantum classifiers
• Quantum random access memory
• Many-body quantum state tomography with neural networks
• Learning phase transitions by confusion
• Quantum computing with atomic qubits and Rydberg interactions: Progress and challenges
• Discovering Phase Transitions with Unsupervised Learning
• Quantum generative adversarial learning
• Hybrid Quantum-Classical Hierarchy for Mitigation of Decoherence and Determination of Excited States
• Quantum machine learning: a classical perspective
• Quantum generative adversarial networks
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Quantum Natural Gradient
• Quantum State Discrimination
• Quantum Entanglement in Neural Network States
• Quantum Circuits for General Multiqubit Gates
• Machine learning quantum phases of matter beyond the fermion sign problem
• Quantum Boltzmann Machine
• Quantum-state preparation with universal gate decompositions
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Efficient Representation of Quantum Many-body States with Deep Neural Networks
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Reconstructing quantum states with generative models
• Architectures for a quantum random access memory
• Hierarchical quantum classifiers
• Machine Learning Topological States
• Differentiable Learning of Quantum Circuit Born Machine
• Quantum generalisation of feedforward neural networks
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Identifying topological order through unsupervised machine learning
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Experimental Realization of Quantum Artificial Intelligence
• Machine Learning Phases of Strongly Correlated Fermions
• Experimental Quantum Hamiltonian Learning
• Implementing a distance-based classifier with a quantum interference circuit
• Realization of 2D Spin-orbit Interaction and Exotic Topological Orders in Cold Atoms
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Seeing topological order in time-of-flight measurements
• Quantum Image Processing and Its Application to Edge Detection: Theory and Experiment
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Quantum generative adversarial learning in a superconducting quantum circuit
• Machine learning meets quantum physics
• Quantum Discriminant Analysis for Dimensionality Reduction and Classification
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Machine Learning ${\mathbb{Z}}_2$ Quantum Spin Liquids with Quasi-particle Statistics
• A Separability-Entanglement Classifier via Machine Learning
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Learning and Inference on Generative Adversarial Quantum Circuits
• Machine Learning Many-Body Localization: Search for the Elusive Nonergodic Metal
• Vulnerability of quantum classification to adversarial perturbations
• Machine Learning Spatial Geometry from Entanglement Features
• Deep Learning Topological Invariants of Band Insulators
• Machine Learning Bell Nonlocality in Quantum Many-body Systems
• Machine Learning Phase Transitions with a Quantum Processor
• Noise Analysis for High-Fidelity Quantum Entangling Gates in an Anharmonic Linear Paul Trap
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Direct Probe of Topological Order for Cold Atoms
• Exponential Orthogonality Catastrophe in Single-Particle and Many-Body Localized Systems
• A quantum active learning algorithm for sampling against adversarial attacks

Cited by in corpus (42)

• Robust data encodings for quantum classifiers
• Quantum noise protects quantum classifiers against adversaries
• Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms
• Quantum federated learning through blind quantum computing
• Experimental quantum adversarial learning with programmable superconducting qubits
• Recent advances for quantum classifiers
• Towards quantum enhanced adversarial robustness in machine learning
• QuGAN: A Quantum State Fidelity based Generative Adversarial Network
• Learning quantum data with the quantum Earth Mover's distance
• Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Markovian Quantum Neuroevolution for Machine Learning
• Quantum Neural Network Classifiers: A Tutorial
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testing
• Robustness Verification of Quantum Classifiers
• Tree tensor network classifiers for machine learning: from quantum-inspired to quantum-assisted
• Quantum Capsule Networks
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning
• Efficient Online Quantum Generative Adversarial Learning Algorithms with Applications
• Efficient Bipartite Entanglement Detection Scheme with a Quantum Adversarial Solver
• Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
• Training robust and generalizable quantum models
• Predominant Aspects on Security for Quantum Machine Learning: Literature Review
• Ensemble-learning error mitigation for variational quantum shallow-circuit classifiers
• Quantum Continual Learning Overcoming Catastrophic Forgetting
• Quantum computing through the lens of control: A tutorial introduction
• Quantum autoencoders for image classification
• Evaluating the Performance of Some Local Optimizers for Variational Quantum Classifiers
• Adversarial Robustness Guarantees for Quantum Classifiers
• Hybrid quantum-classical unsupervised data clustering based on the self-organizing feature map
• QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• A Unified Framework for Quantum Supervised Learning
• Revisiting the dynamics of Bose-Einstein condensates in a double well by deep learning with a hybrid network
• Differentiable Architecture Search for Adversarially Robust Quantum Computer Vision
• Modeling stochastic eye tracking data: A comparison of quantum generative adversarial networks and Markov models
• Quantum-Inspired Weight-Constrained Neural Network: Reducing Variable Numbers by 100x Compared to Standard Neural Networks
• Classical Autoencoder Distillation of Quantum Adversarial Manipulations
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning
• Verifying Adversarial Robustness in Quantum Machine Learning: from theory to physical validation via a software tool