FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386699405> ?p ?o ?g. }

• W4386699405 endingPage "17" @default.
• W4386699405 startingPage "1" @default.
• W4386699405 abstract "Several side-channel attacks exploiting timing, cache, or power side channels have recently been proposed to obtain private information of a neural network. However, the hardware-based attacks require physical access to the system, using high-precision equipment to measure physical system behaviors such as power consumption or electromagnetic emanations, to exploit them as side channels. Whereas, the previous software-based side-channel attacks on neural networks can extract their model information only when the target architecture is known. In this paper, we propose the <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><inline-formula><tex-math notation=LaTeX>$gamma$</tex-math></inline-formula>-Knife attack</i> , a software-based power side-channel attack on a neural network, which can extract its architecture without any physical access or high-precision measuring equipment. Our work demonstrates that side-channels can be formed that leak architecture of neural networks by utilizing statistical metrics without high-resolution power data. The <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$gamma$</tex-math></inline-formula> -Knife attack can reduce the search space of candidate architectures by obtaining private information such as filter size, depth of convolutional layer, and activation functions in the target architecture, as accurately as hardware-based power side-channel attacks even when the target neural network is totally unknown. We demonstrated the efficacy of the <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$gamma$</tex-math></inline-formula> -Knife attack by implementing the attack on the well-known neural networks VGGNet, ResNet, GoogleNet, and MobileNet, using the Pytorch library on Intel CPUs and AMD CPUs. The <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$gamma$</tex-math></inline-formula> -Knife attack could identify the target neural network architecture with an accuracy of approximately 90%, and efficiently extract its private information, by significantly reducing the search space of the target architecture." @default.
• W4386699405 created "2023-09-14" @default.
• W4386699405 creator A5020202918 @default.
• W4386699405 creator A5035201792 @default.
• W4386699405 creator A5059902523 @default.
• W4386699405 date "2023-01-01" @default.
• W4386699405 modified "2023-10-18" @default.
• W4386699405 title "<i>$gamma$-Knife:</i> Extracting Neural Network Architecture Through Software-Based Power Side-Channel" @default.
• W4386699405 doi "https://doi.org/10.1109/tdsc.2023.3314710" @default.
• W4386699405 hasPublicationYear "2023" @default.
• W4386699405 type Work @default.
• W4386699405 citedByCount "0" @default.
• W4386699405 crossrefType "journal-article" @default.
• W4386699405 hasAuthorship W4386699405A5020202918 @default.
• W4386699405 hasAuthorship W4386699405A5035201792 @default.
• W4386699405 hasAuthorship W4386699405A5059902523 @default.
• W4386699405 hasConcept C11413529 @default.
• W4386699405 hasConcept C127162648 @default.
• W4386699405 hasConcept C149635348 @default.
• W4386699405 hasConcept C154945302 @default.
• W4386699405 hasConcept C178489894 @default.
• W4386699405 hasConcept C199360897 @default.
• W4386699405 hasConcept C2777904410 @default.
• W4386699405 hasConcept C31258907 @default.
• W4386699405 hasConcept C41008148 @default.
• W4386699405 hasConcept C49289754 @default.
• W4386699405 hasConcept C50644808 @default.
• W4386699405 hasConcept C81363708 @default.
• W4386699405 hasConcept C9390403 @default.
• W4386699405 hasConceptScore W4386699405C11413529 @default.
• W4386699405 hasConceptScore W4386699405C127162648 @default.
• W4386699405 hasConceptScore W4386699405C149635348 @default.
• W4386699405 hasConceptScore W4386699405C154945302 @default.
• W4386699405 hasConceptScore W4386699405C178489894 @default.
• W4386699405 hasConceptScore W4386699405C199360897 @default.
• W4386699405 hasConceptScore W4386699405C2777904410 @default.
• W4386699405 hasConceptScore W4386699405C31258907 @default.
• W4386699405 hasConceptScore W4386699405C41008148 @default.
• W4386699405 hasConceptScore W4386699405C49289754 @default.
• W4386699405 hasConceptScore W4386699405C50644808 @default.
• W4386699405 hasConceptScore W4386699405C81363708 @default.
• W4386699405 hasConceptScore W4386699405C9390403 @default.
• W4386699405 hasLocation W43866994051 @default.
• W4386699405 hasOpenAccess W4386699405 @default.
• W4386699405 hasPrimaryLocation W43866994051 @default.
• W4386699405 hasRelatedWork W2350333970 @default.
• W4386699405 hasRelatedWork W2350961105 @default.
• W4386699405 hasRelatedWork W2390965452 @default.
• W4386699405 hasRelatedWork W2748454020 @default.
• W4386699405 hasRelatedWork W2780340867 @default.
• W4386699405 hasRelatedWork W2978757589 @default.
• W4386699405 hasRelatedWork W3016958897 @default.
• W4386699405 hasRelatedWork W3181746755 @default.
• W4386699405 hasRelatedWork W4283379348 @default.
• W4386699405 hasRelatedWork W4312417841 @default.
• W4386699405 isParatext "false" @default.
• W4386699405 isRetracted "false" @default.
• W4386699405 workType "article" @default.