Universal Adversarial Examples and Perturbations for Quantum Classifiers

Abstract

Quantum machine learning explores the interplay between machine learning and quantum physics, which may lead to unprecedented perspectives for both fields. In fact, recent works have shown strong evidences that quantum computers could outperform classical computers in solving certain notable machine learning tasks. Yet, quantum learning systems may also suffer from the vulnerability problem: adding a tiny carefully-crafted perturbation to the legitimate input data would cause the systems to make incorrect predictions at a notably high confidence level. In this paper, we study the universality of adversarial examples and perturbations for quantum classifiers. Through concrete examples involving classifications of real-life images and quantum phases of matter, we show that there exist universal adversarial examples that can fool a set of different quantum classifiers. We prove that for a set of $k$ classifiers with each receiving input data of $n$ qubits, an $O(\frac{\ln k}{2^n})$ increase of the perturbation strength is enough to ensure a moderate universal adversarial risk. In addition, for a given quantum classifier we show that there exist universal adversarial perturbations, which can be added to different legitimate samples and make them to be adversarial examples for the classifier. Our results reveal the universality perspective of adversarial attacks for quantum machine learning systems, which would be crucial for practical applications of both near-term and future quantum technologies in solving machine learning problems.

References in corpus (55)

• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Quantum Machine Learning
• Quantum algorithm for solving linear systems of equations
• Supervised learning with quantum enhanced feature spaces
• Quantum computational advantage using photons
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Quantum support vector machine for big data classification
• Quantum machine learning in feature Hilbert spaces
• Quantum Circuit Learning
• On the Convergence of Adam and Beyond
• Quantum Convolutional Neural Networks
• Machine learning phases of matter
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Quantum principal component analysis
• Circuit-centric quantum classifiers
• Quantum random access memory
• Many-body quantum state tomography with neural networks
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Quantum generative adversarial learning
• Quantum algorithms for supervised and unsupervised machine learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Quantum Natural Gradient
• Quantum-enhanced machine learning
• Adversarial Attacks and Defences: A Survey
• Quantum Circuits for General Multiqubit Gates
• Machine learning quantum phases of matter beyond the fermion sign problem
• Quantum-state preparation with universal gate decompositions
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Architectures for a quantum random access memory
• Differentiable Learning of Quantum Circuit Born Machine
• Quantum generalisation of feedforward neural networks
• An Artificial Neuron Implemented on an Actual Quantum Processor
• Quantum Loop Topography for Machine Learning
• Creating superpositions that correspond to efficiently integrable probability distributions
• Training of Quantum Circuits on a Hybrid Quantum Computer
• Quantum generative adversarial learning in a superconducting quantum circuit
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Unsupervised machine learning and band topology
• Quantum noise protects quantum classifiers against adversaries
• Approximation by Quantum Circuits
• Quantum Discriminant Analysis for Dimensionality Reduction and Classification
• Low-depth gradient measurements can improve convergence in variational hybrid quantum-classical algorithms
• Topological Quantum Compiling with Reinforcement Learning
• Vulnerability of quantum classification to adversarial perturbations
• Machine Learning Bell Nonlocality in Quantum Many-body Systems
• Machine Learning Phase Transitions with a Quantum Processor
• Machine Learning Topological Phases with a Solid-state Quantum Simulator
• Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
• On the natural gradient for variational quantum eigensolver
• Inductive supervised quantum learning
• Adversarial Learning in Statistical Classification: A Comprehensive Review of Defenses Against Attacks
• No Free Lunch for Quantum Machine Learning

Cited by in corpus (11)

• Experimental quantum adversarial learning with programmable superconducting qubits
• Recent advances for quantum classifiers
• Towards quantum enhanced adversarial robustness in machine learning
• 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
• QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
• Generating Universal Adversarial Perturbations for Quantum Classifiers
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning