Universal adversarial perturbations for multiple classification tasks with quantum classifiers

Abstract

Quantum adversarial machine learning is an emerging field that studies the vulnerability of quantum learning systems against adversarial perturbations and develops possible defense strategies. Quantum universal adversarial perturbations are small perturbations, which can make different input samples into adversarial examples that may deceive a given quantum classifier. This is a field that was rarely looked into but worthwhile investigating because universal perturbations might simplify malicious attacks to a large extent, causing unexpected devastation to quantum machine learning models. In this paper, we take a step forward and explore the quantum universal perturbations in the context of heterogeneous classification tasks. In particular, we find that quantum classifiers that achieve almost state-of-the-art accuracy on two different classification tasks can be both conclusively deceived by one carefully-crafted universal perturbation. This result is explicitly demonstrated with well-designed quantum continual learning models with elastic weight consolidation method to avoid catastrophic forgetting, as well as real-life heterogeneous datasets from hand-written digits and medical MRI images. Our results provide a simple and efficient way to generate universal perturbations on heterogeneous classification tasks and thus would provide valuable guidance for future quantum learning technologies.

References in corpus (29)

• Adam: A Method for Stochastic Optimization
• Explaining and Harnessing Adversarial Examples
• Overcoming catastrophic forgetting in neural networks
• Quantum Machine Learning
• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• Quantum Fisher information matrix and multiparameter estimation
• Challenges and Opportunities in Quantum Machine Learning
• Quantum advantage in learning from experiments
• Quantum Entanglement in Neural Network States
• MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
• Provably efficient machine learning for quantum many-body problems
• Quantum noise protects quantum classifiers against adversaries
• Machine learning meets quantum physics
• Introduction to quantum Fisher information
• Quantum Adversarial Machine Learning
• Yao.jl: Extensible, Efficient Framework for Quantum Algorithm Design
• Fast simulation of truncated Gaussian distributions
• Experimental quantum adversarial learning with programmable superconducting qubits
• Simple expression for the quantum Fisher information matrix
• Quantum Neural Network Classifiers: A Tutorial
• Deep quantum neural networks equipped with backpropagation on a superconducting processor
• Robust in Practice: Adversarial Attacks on Quantum Machine Learning
• Robustness Verification of Quantum Classifiers
• Universal Adversarial Examples and Perturbations for Quantum Classifiers
• Quantum Capsule Networks
• Quantum Continual Learning Overcoming Catastrophic Forgetting
• Experimental demonstration of adversarial examples in learning topological phases
• Adversarial Machine Learning Phases of Matter
• Enhancing Quantum Adversarial Robustness by Randomized Encodings