METHOD FOR EXTRACTING ARTIFICIAL NEURAL NETWORK BY USING MELTDOWN VULNERABILITY
An artificial neural network extraction method is disclosed. The artificial neural network extraction method is performed by a computing device which can communicate with a server for providing Machine-Learning-as-a-Service (MLaaS) and which includes at least a processor, the method comprising the s...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Patent |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | JEONG, Hoyong RYU, Do-Hyun HUR, Junbeom |
description | An artificial neural network extraction method is disclosed. The artificial neural network extraction method is performed by a computing device which can communicate with a server for providing Machine-Learning-as-a-Service (MLaaS) and which includes at least a processor, the method comprising the steps of: acquiring a page table of a process to be attacked; acquiring, on the basis of the page table, heap area data of the process to be attacked; acquiring, on the basis of the heap area data, an artificial neural network instance of the process to be attacked; and extracting a structure of an artificial neural network model on the basis of the artificial neural network instance. |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024220627A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024220627A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024220627A13</originalsourceid><addsrcrecordid>eNrjZPD3dQ3x8HdRcPMPUnCNCAlydA7x9HNXcAwK8XTzdPZ09FHwcw0NAlMh4f5B3gpOkQqhwSAlvq4-IS7-4X4KYaE-fq5Bjk6ePp4hkTwMrGmJOcWpvFCam0HZzTXE2UM3tSA_PrW4IDE5NS-1JD402MjAyMTIyMDMyNzR0Jg4VQAxLDAf</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD FOR EXTRACTING ARTIFICIAL NEURAL NETWORK BY USING MELTDOWN VULNERABILITY</title><source>esp@cenet</source><creator>JEONG, Hoyong ; RYU, Do-Hyun ; HUR, Junbeom</creator><creatorcontrib>JEONG, Hoyong ; RYU, Do-Hyun ; HUR, Junbeom</creatorcontrib><description>An artificial neural network extraction method is disclosed. The artificial neural network extraction method is performed by a computing device which can communicate with a server for providing Machine-Learning-as-a-Service (MLaaS) and which includes at least a processor, the method comprising the steps of: acquiring a page table of a process to be attacked; acquiring, on the basis of the page table, heap area data of the process to be attacked; acquiring, on the basis of the heap area data, an artificial neural network instance of the process to be attacked; and extracting a structure of an artificial neural network model on the basis of the artificial neural network instance.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240704&DB=EPODOC&CC=US&NR=2024220627A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25569,76552</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240704&DB=EPODOC&CC=US&NR=2024220627A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>JEONG, Hoyong</creatorcontrib><creatorcontrib>RYU, Do-Hyun</creatorcontrib><creatorcontrib>HUR, Junbeom</creatorcontrib><title>METHOD FOR EXTRACTING ARTIFICIAL NEURAL NETWORK BY USING MELTDOWN VULNERABILITY</title><description>An artificial neural network extraction method is disclosed. The artificial neural network extraction method is performed by a computing device which can communicate with a server for providing Machine-Learning-as-a-Service (MLaaS) and which includes at least a processor, the method comprising the steps of: acquiring a page table of a process to be attacked; acquiring, on the basis of the page table, heap area data of the process to be attacked; acquiring, on the basis of the heap area data, an artificial neural network instance of the process to be attacked; and extracting a structure of an artificial neural network model on the basis of the artificial neural network instance.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPD3dQ3x8HdRcPMPUnCNCAlydA7x9HNXcAwK8XTzdPZ09FHwcw0NAlMh4f5B3gpOkQqhwSAlvq4-IS7-4X4KYaE-fq5Bjk6ePp4hkTwMrGmJOcWpvFCam0HZzTXE2UM3tSA_PrW4IDE5NS-1JD402MjAyMTIyMDMyNzR0Jg4VQAxLDAf</recordid><startdate>20240704</startdate><enddate>20240704</enddate><creator>JEONG, Hoyong</creator><creator>RYU, Do-Hyun</creator><creator>HUR, Junbeom</creator><scope>EVB</scope></search><sort><creationdate>20240704</creationdate><title>METHOD FOR EXTRACTING ARTIFICIAL NEURAL NETWORK BY USING MELTDOWN VULNERABILITY</title><author>JEONG, Hoyong ; RYU, Do-Hyun ; HUR, Junbeom</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024220627A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>JEONG, Hoyong</creatorcontrib><creatorcontrib>RYU, Do-Hyun</creatorcontrib><creatorcontrib>HUR, Junbeom</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>JEONG, Hoyong</au><au>RYU, Do-Hyun</au><au>HUR, Junbeom</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD FOR EXTRACTING ARTIFICIAL NEURAL NETWORK BY USING MELTDOWN VULNERABILITY</title><date>2024-07-04</date><risdate>2024</risdate><abstract>An artificial neural network extraction method is disclosed. The artificial neural network extraction method is performed by a computing device which can communicate with a server for providing Machine-Learning-as-a-Service (MLaaS) and which includes at least a processor, the method comprising the steps of: acquiring a page table of a process to be attacked; acquiring, on the basis of the page table, heap area data of the process to be attacked; acquiring, on the basis of the heap area data, an artificial neural network instance of the process to be attacked; and extracting a structure of an artificial neural network model on the basis of the artificial neural network instance.</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | eng |
recordid | cdi_epo_espacenet_US2024220627A1 |
source | esp@cenet |
subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
title | METHOD FOR EXTRACTING ARTIFICIAL NEURAL NETWORK BY USING MELTDOWN VULNERABILITY |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-11T11%3A14%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=JEONG,%20Hoyong&rft.date=2024-07-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024220627A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |