Benchmarking Adversarially Robust Quantum Machine Learning at Scale

• URL: http://arxiv.org/abs/2211.12681v1
• Date: Wed, 23 Nov 2022 03:26:16 GMT
• Title: Benchmarking Adversarially Robust Quantum Machine Learning at Scale
• Authors: Maxwell T. West, Sarah M. Erfani, Christopher Leckie, Martin Sevior, Lloyd C.L. Hollenberg, Muhammad Usman
• Abstract summary: We benchmark the robustness of quantum ML networks at scale by performing rigorous training for both simple and complex image datasets. Our results show that QVCs offer a notably enhanced robustness against classical adversarial attacks. By combining quantum and classical network outcomes, we propose a novel adversarial attack detection technology.
• Score: 20.76790069530767
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning (ML) methods such as artificial neural networks are rapidly becoming ubiquitous in modern science, technology and industry. Despite their accuracy and sophistication, neural networks can be easily fooled by carefully designed malicious inputs known as adversarial attacks. While such vulnerabilities remain a serious challenge for classical neural networks, the extent of their existence is not fully understood in the quantum ML setting. In this work, we benchmark the robustness of quantum ML networks, such as quantum variational classifiers (QVC), at scale by performing rigorous training for both simple and complex image datasets and through a variety of high-end adversarial attacks. Our results show that QVCs offer a notably enhanced robustness against classical adversarial attacks by learning features which are not detected by the classical neural networks, indicating a possible quantum advantage for ML tasks. Contrarily, and remarkably, the converse is not true, with attacks on quantum networks also capable of deceiving classical neural networks. By combining quantum and classical network outcomes, we propose a novel adversarial attack detection technology. Traditionally quantum advantage in ML systems has been sought through increased accuracy or algorithmic speed-up, but our work has revealed the potential for a new kind of quantum advantage through superior robustness of ML models, whose practical realisation will address serious security concerns and reliability issues of ML algorithms employed in a myriad of applications including autonomous vehicles, cybersecurity, and surveillance robotic systems.

Related papers

• QML-IDS: Quantum Machine Learning Intrusion Detection System [1.2016264781280588]
  We present QML-IDS, a novel Intrusion Detection System that combines quantum and classical computing techniques. QML-IDS employs Quantum Machine Learning(QML) methodologies to analyze network patterns and detect attack activities. We show that QML-IDS is effective at attack detection and performs well in binary and multiclass classification tasks.
  arXiv  Detail & Related papers  (2024-10-07T13:07:41Z)
• CTRQNets & LQNets: Continuous Time Recurrent and Liquid Quantum Neural Networks [76.53016529061821]
  Liquid Quantum Neural Network (LQNet) and Continuous Time Recurrent Quantum Neural Network (CTRQNet) developed. LQNet and CTRQNet achieve accuracy increases as high as 40% on CIFAR 10 through binary classification.
  arXiv  Detail & Related papers  (2024-08-28T00:56:03Z)
• RobQuNNs: A Methodology for Robust Quanvolutional Neural Networks against Adversarial Attacks [3.9554540293311864]
  Quanvolutional Neural Networks (QuNNs) integrate quantum and classical layers. This study introduces RobQuNN, a new methodology to enhance the robustness of QuNNs against adversarial attacks. The findings reveal that QuNNs exhibit up to 60% higher robustness compared to classical networks for the MNIST dataset.
  arXiv  Detail & Related papers  (2024-07-04T12:13:52Z)
• ShadowNet for Data-Centric Quantum System Learning [188.683909185536]
  We propose a data-centric learning paradigm combining the strength of neural-network protocols and classical shadows. Capitalizing on the generalization power of neural networks, this paradigm can be trained offline and excel at predicting previously unseen systems. We present the instantiation of our paradigm in quantum state tomography and direct fidelity estimation tasks and conduct numerical analysis up to 60 qubits.
  arXiv  Detail & Related papers  (2023-08-22T09:11:53Z)
• On the Interpretability of Quantum Neural Networks [0.0]
  Interpretability of artificial intelligence (AI) methods, particularly deep neural networks, is of great interest. Here, we explore the interpretability of quantum neural networks using local model-agnostic interpretability measures commonly utilized for classical neural networks. A feature of our explanations is the delineation of the region in which data samples have been given a random label, likely subjects of inherently random quantum measurements.
  arXiv  Detail & Related papers  (2023-08-22T00:43:14Z)
• Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification [83.20479832949069]
  Quantum neural networks (QNNs) have become an important tool for understanding the physical world, but their advantages and limitations are not fully understood. Here we investigate the problem-dependent power of QCs on multi-class classification tasks. Our work sheds light on the problem-dependent power of QNNs and offers a practical tool for evaluating their potential merit.
  arXiv  Detail & Related papers  (2022-12-29T10:46:40Z)
• Recent Advances for Quantum Neural Networks in Generative Learning [98.88205308106778]
  Quantum generative learning models (QGLMs) may surpass their classical counterparts. We review the current progress of QGLMs from the perspective of machine learning. We discuss the potential applications of QGLMs in both conventional machine learning tasks and quantum physics.
  arXiv  Detail & Related papers  (2022-06-07T07:32:57Z)
• Experimental quantum adversarial learning with programmable superconducting qubits [15.24718195264974]
  We show the first experimental demonstration of quantum adversarial learning with programmable superconducting qubits. Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios.
  arXiv  Detail & Related papers  (2022-04-04T18:00:00Z)
• Hybrid Quantum-Classical Neural Network for Cloud-supported In-Vehicle Cyberattack Detection [3.09487092349687]
  In a cloud-supported cyber-physical system environment, running a machine learning application in quantum computers is often difficult. We show that using the hybrid quantum classical NN, it is possible to achieve an attack detection accuracy of 94%.
  arXiv  Detail & Related papers  (2021-10-14T15:40:33Z)
• The dilemma of quantum neural networks [63.82713636522488]
  We show that quantum neural networks (QNNs) fail to provide any benefit over classical learning models. QNNs suffer from the severely limited effective model capacity, which incurs poor generalization on real-world datasets. These results force us to rethink the role of current QNNs and to design novel protocols for solving real-world problems with quantum advantages.
  arXiv  Detail & Related papers  (2021-06-09T10:41:47Z)
• Entanglement Classification via Neural Network Quantum States [58.720142291102135]
  In this paper we combine machine-learning tools and the theory of quantum entanglement to perform entanglement classification for multipartite qubit systems in pure states. We use a parameterisation of quantum systems using artificial neural networks in a restricted Boltzmann machine (RBM) architecture, known as Neural Network Quantum States (NNS)
  arXiv  Detail & Related papers  (2019-12-31T07:40:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.