Detecting Adversarial Attacks through Decoy Training

Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Stoecklin, Marc Philippe, Araujo, Frederico, Zhang, Jialong, Taylor, Teryl
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC COMMUNICATION TECHNIQUE ELECTRIC DIGITAL DATA PROCESSING ELECTRICITY PHYSICS TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
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	Stoecklin, Marc Philippe Araujo, Frederico Zhang, Jialong Taylor, Teryl
description	Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2023019198A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2023019198A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2023019198A13</originalsourceid><addsrcrecordid>eNrjZDBxSS1JTS7JzEtXcEwpSy0qTizKTMxRcCwpSUzOLlYoySjKL03PUHBJTc6vVAgpSszMAyrlYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkbGBoaWhpYWjobGxKkCAOFbLbY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Detecting Adversarial Attacks through Decoy Training</title><source>esp@cenet</source><creator>Stoecklin, Marc Philippe ; Araujo, Frederico ; Zhang, Jialong ; Taylor, Teryl</creator><creatorcontrib>Stoecklin, Marc Philippe ; Araujo, Frederico ; Zhang, Jialong ; Taylor, Teryl</creatorcontrib><description>Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC COMMUNICATION TECHNIQUE ; ELECTRIC DIGITAL DATA PROCESSING ; ELECTRICITY ; PHYSICS ; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</subject><creationdate>2023</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=20230119&DB=EPODOC&CC=US&NR=2023019198A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230119&DB=EPODOC&CC=US&NR=2023019198A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Stoecklin, Marc Philippe</creatorcontrib><creatorcontrib>Araujo, Frederico</creatorcontrib><creatorcontrib>Zhang, Jialong</creatorcontrib><creatorcontrib>Taylor, Teryl</creatorcontrib><title>Detecting Adversarial Attacks through Decoy Training</title><description>Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC COMMUNICATION TECHNIQUE</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>ELECTRICITY</subject><subject>PHYSICS</subject><subject>TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDBxSS1JTS7JzEtXcEwpSy0qTizKTMxRcCwpSUzOLlYoySjKL03PUHBJTc6vVAgpSszMAyrlYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkbGBoaWhpYWjobGxKkCAOFbLbY</recordid><startdate>20230119</startdate><enddate>20230119</enddate><creator>Stoecklin, Marc Philippe</creator><creator>Araujo, Frederico</creator><creator>Zhang, Jialong</creator><creator>Taylor, Teryl</creator><scope>EVB</scope></search><sort><creationdate>20230119</creationdate><title>Detecting Adversarial Attacks through Decoy Training</title><author>Stoecklin, Marc Philippe ; Araujo, Frederico ; Zhang, Jialong ; Taylor, Teryl</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2023019198A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC COMMUNICATION TECHNIQUE</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>ELECTRICITY</topic><topic>PHYSICS</topic><topic>TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</topic><toplevel>online_resources</toplevel><creatorcontrib>Stoecklin, Marc Philippe</creatorcontrib><creatorcontrib>Araujo, Frederico</creatorcontrib><creatorcontrib>Zhang, Jialong</creatorcontrib><creatorcontrib>Taylor, Teryl</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Stoecklin, Marc Philippe</au><au>Araujo, Frederico</au><au>Zhang, Jialong</au><au>Taylor, Teryl</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Detecting Adversarial Attacks through Decoy Training</title><date>2023-01-19</date><risdate>2023</risdate><abstract>Decoy data is generated from regular data. A deep neural network, which has been trained with the regular data, is trained with the decoy data. The trained deep neural network, responsive to a client request comprising input data, is operated on the input data. Post-processing is performed using at least an output of the operated trained deep neural network to determine whether the input data is regular data or decoy data. One or more actions are performed based on a result of the performed post-processing.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2023019198A1
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC COMMUNICATION TECHNIQUE ELECTRIC DIGITAL DATA PROCESSING ELECTRICITY PHYSICS TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
title	Detecting Adversarial Attacks through Decoy Training
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T16%3A29%3A00IST&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=Stoecklin,%20Marc%20Philippe&rft.date=2023-01-19&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2023019198A1%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