Hybrid Classical Quantum Neural Network with High Adversarial Robustness

Yang Yongxi, Zhang Shibin, Yan Lili, Chang Yan
Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing, PMLR 245:271-279, 2024.

Abstract

As the realms of quantum computing and machine learning converge, a novel domain, termed quantum machine learning, is progressively forming within the sphere of artificial intelligence studies. Nonetheless, akin to its classical counterpart, this emerging field is not exempt from security vulnerabilities. Quantum machine learning systems, regardless of whether they process classical or quantum inputs, are susceptible to minor perturbations that can erroneously skew classification outcomes. These minute disruptions, often imperceptible to human observation, present a significant challenge in ensuring the integrity of quantum classifiers. As the complexity of quantum classifiers increases, their vulnerability also gradually grows. To mitigate this issue, this paper proposes a novel hybrid classical-quantum neural network model that enhances the model’s adversarial robustness by adding a preprocessing layer for noise reduction and data reconstruction. Experiments demonstrate that this model exhibits higher efficiency and accuracy in noisy environments and against adversarial attacks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v245-yongxi24a, title = {Hybrid Classical Quantum Neural Network with High Adversarial Robustness}, author = {Yongxi, Yang and Shibin, Zhang and Lili, Yan and Yan, Chang}, booktitle = {Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing}, pages = {271--279}, year = {2024}, editor = {Nianyin, Zeng and Pachori, Ram Bilas}, volume = {245}, series = {Proceedings of Machine Learning Research}, month = {26--28 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v245/main/assets/yongxi24a/yongxi24a.pdf}, url = {https://proceedings.mlr.press/v245/yongxi24a.html}, abstract = {As the realms of quantum computing and machine learning converge, a novel domain, termed quantum machine learning, is progressively forming within the sphere of artificial intelligence studies. Nonetheless, akin to its classical counterpart, this emerging field is not exempt from security vulnerabilities. Quantum machine learning systems, regardless of whether they process classical or quantum inputs, are susceptible to minor perturbations that can erroneously skew classification outcomes. These minute disruptions, often imperceptible to human observation, present a significant challenge in ensuring the integrity of quantum classifiers. As the complexity of quantum classifiers increases, their vulnerability also gradually grows. To mitigate this issue, this paper proposes a novel hybrid classical-quantum neural network model that enhances the model’s adversarial robustness by adding a preprocessing layer for noise reduction and data reconstruction. Experiments demonstrate that this model exhibits higher efficiency and accuracy in noisy environments and against adversarial attacks.} }
Endnote
%0 Conference Paper %T Hybrid Classical Quantum Neural Network with High Adversarial Robustness %A Yang Yongxi %A Zhang Shibin %A Yan Lili %A Chang Yan %B Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2024 %E Zeng Nianyin %E Ram Bilas Pachori %F pmlr-v245-yongxi24a %I PMLR %P 271--279 %U https://proceedings.mlr.press/v245/yongxi24a.html %V 245 %X As the realms of quantum computing and machine learning converge, a novel domain, termed quantum machine learning, is progressively forming within the sphere of artificial intelligence studies. Nonetheless, akin to its classical counterpart, this emerging field is not exempt from security vulnerabilities. Quantum machine learning systems, regardless of whether they process classical or quantum inputs, are susceptible to minor perturbations that can erroneously skew classification outcomes. These minute disruptions, often imperceptible to human observation, present a significant challenge in ensuring the integrity of quantum classifiers. As the complexity of quantum classifiers increases, their vulnerability also gradually grows. To mitigate this issue, this paper proposes a novel hybrid classical-quantum neural network model that enhances the model’s adversarial robustness by adding a preprocessing layer for noise reduction and data reconstruction. Experiments demonstrate that this model exhibits higher efficiency and accuracy in noisy environments and against adversarial attacks.
APA
Yongxi, Y., Shibin, Z., Lili, Y. & Yan, C.. (2024). Hybrid Classical Quantum Neural Network with High Adversarial Robustness. Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 245:271-279 Available from https://proceedings.mlr.press/v245/yongxi24a.html.

Related Material