FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296831820> ?p ?o ?g. }

• W4296831820 endingPage "383" @default.
• W4296831820 startingPage "364" @default.
• W4296831820 abstract "With growing popularity, deep learning (DL) models are becoming larger-scale, and only the companies with vast training datasets and immense computing power can manage their business serving such large models. Most of those DL models are proprietary to the companies who thus strive to keep their private models safe from the model extraction attack (MEA), whose aim is to steal the model by training surrogate models. Nowadays, companies are inclined to offload the models from central servers to edge/endpoint devices. As revealed in the latest studies, adversaries exploit this opportunity as new attack vectors to launch side-channel attack (SCA) on the device running victim model and obtain various pieces of the model information, such as the model architecture (MA) and image dimension (ID). Our work provides a comprehensive understanding of such a relationship for the first time and would benefit future MEA studies in both offensive and defensive sides in that they may learn which pieces of information exposed by SCA are more important than the others. Our analysis additionally reveals that by grasping the victim model information from SCA, MEA can get highly effective and successful even without any prior knowledge of the model. Finally, to evince the practicality of our analysis results, we empirically apply SCA, and subsequently, carry out MEA under realistic threat assumptions. The results show up to 5.8 times better performance than when the adversary has no model information about the victim model." @default.
• W4296831820 created "2022-09-24" @default.
• W4296831820 creator A5002034433 @default.
• W4296831820 creator A5020736659 @default.
• W4296831820 creator A5042587361 @default.
• W4296831820 creator A5047475163 @default.
• W4296831820 creator A5082524666 @default.
• W4296831820 creator A5083736833 @default.
• W4296831820 date "2022-01-01" @default.
• W4296831820 modified "2023-09-29" @default.
• W4296831820 title "Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices" @default.
• W4296831820 cites W2034195502 @default.
• W4296831820 cites W2117539524 @default.
• W4296831820 cites W2152161678 @default.
• W4296831820 cites W2194775991 @default.
• W4296831820 cites W2294710185 @default.
• W4296831820 cites W2603766943 @default.
• W4296831820 cites W2747590145 @default.
• W4296831820 cites W2808195004 @default.
• W4296831820 cites W2963303354 @default.
• W4296831820 cites W2964137095 @default.
• W4296831820 cites W2997146418 @default.
• W4296831820 cites W3007318395 @default.
• W4296831820 cites W3046768359 @default.
• W4296831820 cites W3102836279 @default.
• W4296831820 cites W4288083516 @default.
• W4296831820 doi "https://doi.org/10.1007/978-3-031-17143-7_18" @default.
• W4296831820 hasPublicationYear "2022" @default.
• W4296831820 type Work @default.
• W4296831820 citedByCount "0" @default.
• W4296831820 crossrefType "book-chapter" @default.
• W4296831820 hasAuthorship W4296831820A5002034433 @default.
• W4296831820 hasAuthorship W4296831820A5020736659 @default.
• W4296831820 hasAuthorship W4296831820A5042587361 @default.
• W4296831820 hasAuthorship W4296831820A5047475163 @default.
• W4296831820 hasAuthorship W4296831820A5082524666 @default.
• W4296831820 hasAuthorship W4296831820A5083736833 @default.
• W4296831820 hasConcept C108583219 @default.
• W4296831820 hasConcept C111919701 @default.
• W4296831820 hasConcept C127413603 @default.
• W4296831820 hasConcept C136764020 @default.
• W4296831820 hasConcept C138236772 @default.
• W4296831820 hasConcept C154945302 @default.
• W4296831820 hasConcept C15744967 @default.
• W4296831820 hasConcept C162307627 @default.
• W4296831820 hasConcept C165696696 @default.
• W4296831820 hasConcept C176856949 @default.
• W4296831820 hasConcept C178489894 @default.
• W4296831820 hasConcept C202444582 @default.
• W4296831820 hasConcept C2524010 @default.
• W4296831820 hasConcept C2780586970 @default.
• W4296831820 hasConcept C28719098 @default.
• W4296831820 hasConcept C33676613 @default.
• W4296831820 hasConcept C33923547 @default.
• W4296831820 hasConcept C38652104 @default.
• W4296831820 hasConcept C41008148 @default.
• W4296831820 hasConcept C41065033 @default.
• W4296831820 hasConcept C42475967 @default.
• W4296831820 hasConcept C49289754 @default.
• W4296831820 hasConcept C77805123 @default.
• W4296831820 hasConcept C79974875 @default.
• W4296831820 hasConcept C93996380 @default.
• W4296831820 hasConceptScore W4296831820C108583219 @default.
• W4296831820 hasConceptScore W4296831820C111919701 @default.
• W4296831820 hasConceptScore W4296831820C127413603 @default.
• W4296831820 hasConceptScore W4296831820C136764020 @default.
• W4296831820 hasConceptScore W4296831820C138236772 @default.
• W4296831820 hasConceptScore W4296831820C154945302 @default.
• W4296831820 hasConceptScore W4296831820C15744967 @default.
• W4296831820 hasConceptScore W4296831820C162307627 @default.
• W4296831820 hasConceptScore W4296831820C165696696 @default.
• W4296831820 hasConceptScore W4296831820C176856949 @default.
• W4296831820 hasConceptScore W4296831820C178489894 @default.
• W4296831820 hasConceptScore W4296831820C202444582 @default.
• W4296831820 hasConceptScore W4296831820C2524010 @default.
• W4296831820 hasConceptScore W4296831820C2780586970 @default.
• W4296831820 hasConceptScore W4296831820C28719098 @default.
• W4296831820 hasConceptScore W4296831820C33676613 @default.
• W4296831820 hasConceptScore W4296831820C33923547 @default.
• W4296831820 hasConceptScore W4296831820C38652104 @default.
• W4296831820 hasConceptScore W4296831820C41008148 @default.
• W4296831820 hasConceptScore W4296831820C41065033 @default.
• W4296831820 hasConceptScore W4296831820C42475967 @default.
• W4296831820 hasConceptScore W4296831820C49289754 @default.
• W4296831820 hasConceptScore W4296831820C77805123 @default.
• W4296831820 hasConceptScore W4296831820C79974875 @default.
• W4296831820 hasConceptScore W4296831820C93996380 @default.
• W4296831820 hasLocation W42968318201 @default.
• W4296831820 hasOpenAccess W4296831820 @default.
• W4296831820 hasPrimaryLocation W42968318201 @default.
• W4296831820 hasRelatedWork W1481299995 @default.
• W4296831820 hasRelatedWork W1980825054 @default.
• W4296831820 hasRelatedWork W2042320372 @default.
• W4296831820 hasRelatedWork W2511315835 @default.
• W4296831820 hasRelatedWork W2831856846 @default.
• W4296831820 hasRelatedWork W2951187092 @default.
• W4296831820 hasRelatedWork W3046853140 @default.
• W4296831820 hasRelatedWork W3134770507 @default.

• next