Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381997526> ?p ?o ?g. }
- W4381997526 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." @default.
- W4381997526 created "2023-06-26" @default.
- W4381997526 creator A5001284915 @default.
- W4381997526 creator A5012865362 @default.
- W4381997526 creator A5041859065 @default.
- W4381997526 creator A5048403895 @default.
- W4381997526 creator A5070030398 @default.
- W4381997526 creator A5076014464 @default.
- W4381997526 date "2023-06-23" @default.
- W4381997526 modified "2023-10-17" @default.
- W4381997526 title "Benchmarking adversarially robust quantum machine learning at scale" @default.
- W4381997526 cites W1492999010 @default.
- W4381997526 cites W2112796928 @default.
- W4381997526 cites W2559394418 @default.
- W4381997526 cites W2761673598 @default.
- W4381997526 cites W2798434869 @default.
- W4381997526 cites W2798967590 @default.
- W4381997526 cites W2809895662 @default.
- W4381997526 cites W2896712926 @default.
- W4381997526 cites W2903221501 @default.
- W4381997526 cites W2919115771 @default.
- W4381997526 cites W2943955321 @default.
- W4381997526 cites W3004965358 @default.
- W4381997526 cites W3007264885 @default.
- W4381997526 cites W3009313620 @default.
- W4381997526 cites W3012697779 @default.
- W4381997526 cites W3019166713 @default.
- W4381997526 cites W3102320711 @default.
- W4381997526 cites W3105870134 @default.
- W4381997526 cites W3116279284 @default.
- W4381997526 cites W3119974792 @default.
- W4381997526 cites W3129004273 @default.
- W4381997526 cites W3157186308 @default.
- W4381997526 cites W3177828909 @default.
- W4381997526 cites W3211718387 @default.
- W4381997526 cites W3217374434 @default.
- W4381997526 cites W4287687381 @default.
- W4381997526 cites W4296126438 @default.
- W4381997526 cites W4300979811 @default.
- W4381997526 cites W4310155627 @default.
- W4381997526 doi "https://doi.org/10.1103/physrevresearch.5.023186" @default.
- W4381997526 hasPublicationYear "2023" @default.
- W4381997526 type Work @default.
- W4381997526 citedByCount "2" @default.
- W4381997526 countsByYear W43819975262023 @default.
- W4381997526 crossrefType "journal-article" @default.
- W4381997526 hasAuthorship W4381997526A5001284915 @default.
- W4381997526 hasAuthorship W4381997526A5012865362 @default.
- W4381997526 hasAuthorship W4381997526A5041859065 @default.
- W4381997526 hasAuthorship W4381997526A5048403895 @default.
- W4381997526 hasAuthorship W4381997526A5070030398 @default.
- W4381997526 hasAuthorship W4381997526A5076014464 @default.
- W4381997526 hasBestOaLocation W43819975261 @default.
- W4381997526 hasConcept C104317684 @default.
- W4381997526 hasConcept C108583219 @default.
- W4381997526 hasConcept C113775141 @default.
- W4381997526 hasConcept C119857082 @default.
- W4381997526 hasConcept C121332964 @default.
- W4381997526 hasConcept C154945302 @default.
- W4381997526 hasConcept C185592680 @default.
- W4381997526 hasConcept C2779462738 @default.
- W4381997526 hasConcept C37736160 @default.
- W4381997526 hasConcept C41008148 @default.
- W4381997526 hasConcept C50644808 @default.
- W4381997526 hasConcept C55493867 @default.
- W4381997526 hasConcept C58053490 @default.
- W4381997526 hasConcept C62520636 @default.
- W4381997526 hasConcept C63479239 @default.
- W4381997526 hasConcept C80444323 @default.
- W4381997526 hasConcept C84114770 @default.
- W4381997526 hasConceptScore W4381997526C104317684 @default.
- W4381997526 hasConceptScore W4381997526C108583219 @default.
- W4381997526 hasConceptScore W4381997526C113775141 @default.
- W4381997526 hasConceptScore W4381997526C119857082 @default.
- W4381997526 hasConceptScore W4381997526C121332964 @default.
- W4381997526 hasConceptScore W4381997526C154945302 @default.
- W4381997526 hasConceptScore W4381997526C185592680 @default.
- W4381997526 hasConceptScore W4381997526C2779462738 @default.
- W4381997526 hasConceptScore W4381997526C37736160 @default.
- W4381997526 hasConceptScore W4381997526C41008148 @default.
- W4381997526 hasConceptScore W4381997526C50644808 @default.
- W4381997526 hasConceptScore W4381997526C55493867 @default.
- W4381997526 hasConceptScore W4381997526C58053490 @default.
- W4381997526 hasConceptScore W4381997526C62520636 @default.
- W4381997526 hasConceptScore W4381997526C63479239 @default.
- W4381997526 hasConceptScore W4381997526C80444323 @default.
- W4381997526 hasConceptScore W4381997526C84114770 @default.
- W4381997526 hasFunder F4320334704 @default.
- W4381997526 hasIssue "2" @default.
- W4381997526 hasLocation W43819975261 @default.
- W4381997526 hasLocation W43819975262 @default.
- W4381997526 hasLocation W43819975263 @default.
- W4381997526 hasOpenAccess W4381997526 @default.
- W4381997526 hasPrimaryLocation W43819975261 @default.
- W4381997526 hasRelatedWork W204679888 @default.
- W4381997526 hasRelatedWork W2989046916 @default.
- W4381997526 hasRelatedWork W2991647176 @default.
- W4381997526 hasRelatedWork W4220701436 @default.
- W4381997526 hasRelatedWork W4281396976 @default.
- W4381997526 hasRelatedWork W4285214172 @default.