TRAINING DATA PROTECTION FOR ARTIFICIAL INTELLIGENCE MODEL IN PARTITIONED EXECUTION ENVIRONMENT

TRAINING DATA PROTECTION FOR ARTIFICIAL INTELLIGENCE MODEL IN PARTITIONED EXECUTION ENVIRONMENT

Techniques for training data protection in an artificial intelligence model execution environment are disclosed. For example, a method comprises executing a first partition of an artificial intelligence model within a secure execution area of an information processing system and a second partition o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jia, Zhen, Liu, Jinpeng, Durazzo, Kenneth, Estrin, Michael
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
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 Jia, Zhen
Liu, Jinpeng
Durazzo, Kenneth
Estrin, Michael
description Techniques for training data protection in an artificial intelligence model execution environment are disclosed. For example, a method comprises executing a first partition of an artificial intelligence model within a secure execution area of an information processing system and a second partition of the artificial intelligence model within a non-secure execution area of the information processing system, wherein data at least one of obtained and processed in the first partition of the artificial intelligence model is inaccessible to the second partition of the artificial intelligence model. Communication between the first partition and the second partition may be enabled via a model parallelism-based procedure. Data obtained in the secure execution area may comprise one or more data samples in an encrypted form usable to train the artificial intelligence model.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2022414223A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2022414223A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2022414223A13</originalsourceid><addsrcrecordid>eNqNy0EKwjAQheFuXIh6hwHXgk17gZBM6kA6KXEq7kKRuBIt1PsjEQ_g6sHP99ZVkqiJiTuwWjQMMQgaocDgQgQdhRwZ0h6IBb2nDtkg9MFiSTAUUThawCua8XtFvlAM3CPLtlrdp8eSd7_dVHuHYk6HPL9SXubplp_5ncazOirV1q1Sja6b_9QHRR00aQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>TRAINING DATA PROTECTION FOR ARTIFICIAL INTELLIGENCE MODEL IN PARTITIONED EXECUTION ENVIRONMENT</title><source>esp@cenet</source><creator>Jia, Zhen ; Liu, Jinpeng ; Durazzo, Kenneth ; Estrin, Michael</creator><creatorcontrib>Jia, Zhen ; Liu, Jinpeng ; Durazzo, Kenneth ; Estrin, Michael</creatorcontrib><description>Techniques for training data protection in an artificial intelligence model execution environment are disclosed. For example, a method comprises executing a first partition of an artificial intelligence model within a secure execution area of an information processing system and a second partition of the artificial intelligence model within a non-secure execution area of the information processing system, wherein data at least one of obtained and processed in the first partition of the artificial intelligence model is inaccessible to the second partition of the artificial intelligence model. Communication between the first partition and the second partition may be enabled via a model parallelism-based procedure. Data obtained in the secure execution area may comprise one or more data samples in an encrypted form usable to train the artificial intelligence model.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2022</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&amp;date=20221229&amp;DB=EPODOC&amp;CC=US&amp;NR=2022414223A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20221229&amp;DB=EPODOC&amp;CC=US&amp;NR=2022414223A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Jia, Zhen</creatorcontrib><creatorcontrib>Liu, Jinpeng</creatorcontrib><creatorcontrib>Durazzo, Kenneth</creatorcontrib><creatorcontrib>Estrin, Michael</creatorcontrib><title>TRAINING DATA PROTECTION FOR ARTIFICIAL INTELLIGENCE MODEL IN PARTITIONED EXECUTION ENVIRONMENT</title><description>Techniques for training data protection in an artificial intelligence model execution environment are disclosed. For example, a method comprises executing a first partition of an artificial intelligence model within a secure execution area of an information processing system and a second partition of the artificial intelligence model within a non-secure execution area of the information processing system, wherein data at least one of obtained and processed in the first partition of the artificial intelligence model is inaccessible to the second partition of the artificial intelligence model. Communication between the first partition and the second partition may be enabled via a model parallelism-based procedure. Data obtained in the secure execution area may comprise one or more data samples in an encrypted form usable to train the artificial intelligence model.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNy0EKwjAQheFuXIh6hwHXgk17gZBM6kA6KXEq7kKRuBIt1PsjEQ_g6sHP99ZVkqiJiTuwWjQMMQgaocDgQgQdhRwZ0h6IBb2nDtkg9MFiSTAUUThawCua8XtFvlAM3CPLtlrdp8eSd7_dVHuHYk6HPL9SXubplp_5ncazOirV1q1Sja6b_9QHRR00aQ</recordid><startdate>20221229</startdate><enddate>20221229</enddate><creator>Jia, Zhen</creator><creator>Liu, Jinpeng</creator><creator>Durazzo, Kenneth</creator><creator>Estrin, Michael</creator><scope>EVB</scope></search><sort><creationdate>20221229</creationdate><title>TRAINING DATA PROTECTION FOR ARTIFICIAL INTELLIGENCE MODEL IN PARTITIONED EXECUTION ENVIRONMENT</title><author>Jia, Zhen ; Liu, Jinpeng ; Durazzo, Kenneth ; Estrin, Michael</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2022414223A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Jia, Zhen</creatorcontrib><creatorcontrib>Liu, Jinpeng</creatorcontrib><creatorcontrib>Durazzo, Kenneth</creatorcontrib><creatorcontrib>Estrin, Michael</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jia, Zhen</au><au>Liu, Jinpeng</au><au>Durazzo, Kenneth</au><au>Estrin, Michael</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>TRAINING DATA PROTECTION FOR ARTIFICIAL INTELLIGENCE MODEL IN PARTITIONED EXECUTION ENVIRONMENT</title><date>2022-12-29</date><risdate>2022</risdate><abstract>Techniques for training data protection in an artificial intelligence model execution environment are disclosed. For example, a method comprises executing a first partition of an artificial intelligence model within a secure execution area of an information processing system and a second partition of the artificial intelligence model within a non-secure execution area of the information processing system, wherein data at least one of obtained and processed in the first partition of the artificial intelligence model is inaccessible to the second partition of the artificial intelligence model. Communication between the first partition and the second partition may be enabled via a model parallelism-based procedure. Data obtained in the secure execution area may comprise one or more data samples in an encrypted form usable to train the artificial intelligence model.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2022414223A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title TRAINING DATA PROTECTION FOR ARTIFICIAL INTELLIGENCE MODEL IN PARTITIONED EXECUTION ENVIRONMENT
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T20%3A22%3A35IST&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=Jia,%20Zhen&rft.date=2022-12-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2022414223A1%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