METHOD AND DATA PROCESSING SYSTEM FOR MAKING MACHINE LEARNING MODEL MORE RESISTENT TO ADVERSARIAL EXAMPLES

METHOD AND DATA PROCESSING SYSTEM FOR MAKING MACHINE LEARNING MODEL MORE RESISTENT TO ADVERSARIAL EXAMPLES

A method and data processing system for making a machine learning model more resistant to adversarial examples are provided. In the method, an input for a machine learning model is provided. A randomly generated mask is added to the input to produce a modified input. The modified input is provided t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Friedberger, Simon Johann, Van Vredendaal, Christine, Kuipers, Christiaan, Veshchikov, Nikita, Bos, Joppe Willem, Verneuil, Vincent, Ermans, Brian
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
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 Friedberger, Simon Johann
Van Vredendaal, Christine
Kuipers, Christiaan
Veshchikov, Nikita
Bos, Joppe Willem
Verneuil, Vincent
Ermans, Brian
description A method and data processing system for making a machine learning model more resistant to adversarial examples are provided. In the method, an input for a machine learning model is provided. A randomly generated mask is added to the input to produce a modified input. The modified input is provided to the machine learning model. The randomly generated mask negates the effect of a perturbation added to the input for causing the input to be an adversarial example. The method may be implemented using the data processing system.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2020293941A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2020293941A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2020293941A13</originalsourceid><addsrcrecordid>eNqNirsKwkAQRdNYiPoPA9aCMTYph92JWdxHmFlFqxBkLUQ0EP8fo_gBcuFcOJxpdnMU66ABvQaNEaHhoEjE-B3IWSI5qAKDw_3HOFS18QSWkP1XBE12JBMwiRl7HyEGQH0kFmSDFuiErrEk82xy7e5DWvx-li0riqpepf7ZpqHvLumRXu1BNutxZVFuc8yL_6o3UbM3DQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD AND DATA PROCESSING SYSTEM FOR MAKING MACHINE LEARNING MODEL MORE RESISTENT TO ADVERSARIAL EXAMPLES</title><source>esp@cenet</source><creator>Friedberger, Simon Johann ; Van Vredendaal, Christine ; Kuipers, Christiaan ; Veshchikov, Nikita ; Bos, Joppe Willem ; Verneuil, Vincent ; Ermans, Brian</creator><creatorcontrib>Friedberger, Simon Johann ; Van Vredendaal, Christine ; Kuipers, Christiaan ; Veshchikov, Nikita ; Bos, Joppe Willem ; Verneuil, Vincent ; Ermans, Brian</creatorcontrib><description>A method and data processing system for making a machine learning model more resistant to adversarial examples are provided. In the method, an input for a machine learning model is provided. A randomly generated mask is added to the input to produce a modified input. The modified input is provided to the machine learning model. The randomly generated mask negates the effect of a perturbation added to the input for causing the input to be an adversarial example. The method may be implemented using the data processing system.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC COMMUNICATION TECHNIQUE ; ELECTRICITY ; PHYSICS ; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</subject><creationdate>2020</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=20200917&amp;DB=EPODOC&amp;CC=US&amp;NR=2020293941A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76418</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20200917&amp;DB=EPODOC&amp;CC=US&amp;NR=2020293941A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Friedberger, Simon Johann</creatorcontrib><creatorcontrib>Van Vredendaal, Christine</creatorcontrib><creatorcontrib>Kuipers, Christiaan</creatorcontrib><creatorcontrib>Veshchikov, Nikita</creatorcontrib><creatorcontrib>Bos, Joppe Willem</creatorcontrib><creatorcontrib>Verneuil, Vincent</creatorcontrib><creatorcontrib>Ermans, Brian</creatorcontrib><title>METHOD AND DATA PROCESSING SYSTEM FOR MAKING MACHINE LEARNING MODEL MORE RESISTENT TO ADVERSARIAL EXAMPLES</title><description>A method and data processing system for making a machine learning model more resistant to adversarial examples are provided. In the method, an input for a machine learning model is provided. A randomly generated mask is added to the input to produce a modified input. The modified input is provided to the machine learning model. The randomly generated mask negates the effect of a perturbation added to the input for causing the input to be an adversarial example. The method may be implemented using the data processing system.</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>ELECTRICITY</subject><subject>PHYSICS</subject><subject>TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNirsKwkAQRdNYiPoPA9aCMTYph92JWdxHmFlFqxBkLUQ0EP8fo_gBcuFcOJxpdnMU66ABvQaNEaHhoEjE-B3IWSI5qAKDw_3HOFS18QSWkP1XBE12JBMwiRl7HyEGQH0kFmSDFuiErrEk82xy7e5DWvx-li0riqpepf7ZpqHvLumRXu1BNutxZVFuc8yL_6o3UbM3DQ</recordid><startdate>20200917</startdate><enddate>20200917</enddate><creator>Friedberger, Simon Johann</creator><creator>Van Vredendaal, Christine</creator><creator>Kuipers, Christiaan</creator><creator>Veshchikov, Nikita</creator><creator>Bos, Joppe Willem</creator><creator>Verneuil, Vincent</creator><creator>Ermans, Brian</creator><scope>EVB</scope></search><sort><creationdate>20200917</creationdate><title>METHOD AND DATA PROCESSING SYSTEM FOR MAKING MACHINE LEARNING MODEL MORE RESISTENT TO ADVERSARIAL EXAMPLES</title><author>Friedberger, Simon Johann ; Van Vredendaal, Christine ; Kuipers, Christiaan ; Veshchikov, Nikita ; Bos, Joppe Willem ; Verneuil, Vincent ; Ermans, Brian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2020293941A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2020</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>ELECTRICITY</topic><topic>PHYSICS</topic><topic>TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION</topic><toplevel>online_resources</toplevel><creatorcontrib>Friedberger, Simon Johann</creatorcontrib><creatorcontrib>Van Vredendaal, Christine</creatorcontrib><creatorcontrib>Kuipers, Christiaan</creatorcontrib><creatorcontrib>Veshchikov, Nikita</creatorcontrib><creatorcontrib>Bos, Joppe Willem</creatorcontrib><creatorcontrib>Verneuil, Vincent</creatorcontrib><creatorcontrib>Ermans, Brian</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Friedberger, Simon Johann</au><au>Van Vredendaal, Christine</au><au>Kuipers, Christiaan</au><au>Veshchikov, Nikita</au><au>Bos, Joppe Willem</au><au>Verneuil, Vincent</au><au>Ermans, Brian</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD AND DATA PROCESSING SYSTEM FOR MAKING MACHINE LEARNING MODEL MORE RESISTENT TO ADVERSARIAL EXAMPLES</title><date>2020-09-17</date><risdate>2020</risdate><abstract>A method and data processing system for making a machine learning model more resistant to adversarial examples are provided. In the method, an input for a machine learning model is provided. A randomly generated mask is added to the input to produce a modified input. The modified input is provided to the machine learning model. The randomly generated mask negates the effect of a perturbation added to the input for causing the input to be an adversarial example. The method may be implemented using the data processing system.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2020293941A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
PHYSICS
TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
title METHOD AND DATA PROCESSING SYSTEM FOR MAKING MACHINE LEARNING MODEL MORE RESISTENT TO ADVERSARIAL EXAMPLES
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T13%3A09%3A01IST&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=Friedberger,%20Simon%20Johann&rft.date=2020-09-17&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2020293941A1%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