METHOD FOR RECOGNIZING AN ADVERSARIAL DISTURBANCE IN INPUT DATA OF A NEURAL NETWORK

A method for detecting an adversarial perturbation in input data of a neural network, wherein a conditional generative adversarial network is trained during a training phase, wherein a generator network of the conditional generative adversarial network is trained to generate adversarial perturbation...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	SCHLICHT, Peter, VARGHESE, John Serin, KAPOOR, Nikhil
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING 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	SCHLICHT, Peter VARGHESE, John Serin KAPOOR, Nikhil
description	A method for detecting an adversarial perturbation in input data of a neural network, wherein a conditional generative adversarial network is trained during a training phase, wherein a generator network of the conditional generative adversarial network is trained to generate adversarial perturbations conditioned on input data of the neural network, and wherein a discriminator network of the conditional generative adversarial network is trained at least to detect an adversarial perturbation in the input data generated by the generator network, and wherein, during an application phase, the trained discriminator network detects an adversarial perturbation in input data of the neural network and provides a detection result. Also disclosed is a backend server, a detection device and a system.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2021042627A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2021042627A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2021042627A13</originalsourceid><addsrcrecordid>eNqNyrEKwjAQgOEuDqK-w4Gz0EbR-UwubVAvckkUXEqROIkW6vtjBx9A-OFfvmkRThQbb8B6ASHta3Y3xzUgA5oLSUBxeATjQkyyR9YEjsfOKYLBiOAtIDAlGRVTvHo5zIvJo3sOefH7rFhairpZ5f7d5qHv7vmVP20KqlRVuVFbtcNq_Z_6AqCnMII</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD FOR RECOGNIZING AN ADVERSARIAL DISTURBANCE IN INPUT DATA OF A NEURAL NETWORK</title><source>esp@cenet</source><creator>SCHLICHT, Peter ; VARGHESE, John Serin ; KAPOOR, Nikhil</creator><creatorcontrib>SCHLICHT, Peter ; VARGHESE, John Serin ; KAPOOR, Nikhil</creatorcontrib><description>A method for detecting an adversarial perturbation in input data of a neural network, wherein a conditional generative adversarial network is trained during a training phase, wherein a generator network of the conditional generative adversarial network is trained to generate adversarial perturbations conditioned on input data of the neural network, and wherein a discriminator network of the conditional generative adversarial network is trained at least to detect an adversarial perturbation in the input data generated by the generator network, and wherein, during an application phase, the trained discriminator network detects an adversarial perturbation in input data of the neural network and provides a detection result. Also disclosed is a backend server, a detection device and a system.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2021</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=20210211&DB=EPODOC&CC=US&NR=2021042627A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210211&DB=EPODOC&CC=US&NR=2021042627A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SCHLICHT, Peter</creatorcontrib><creatorcontrib>VARGHESE, John Serin</creatorcontrib><creatorcontrib>KAPOOR, Nikhil</creatorcontrib><title>METHOD FOR RECOGNIZING AN ADVERSARIAL DISTURBANCE IN INPUT DATA OF A NEURAL NETWORK</title><description>A method for detecting an adversarial perturbation in input data of a neural network, wherein a conditional generative adversarial network is trained during a training phase, wherein a generator network of the conditional generative adversarial network is trained to generate adversarial perturbations conditioned on input data of the neural network, and wherein a discriminator network of the conditional generative adversarial network is trained at least to detect an adversarial perturbation in the input data generated by the generator network, and wherein, during an application phase, the trained discriminator network detects an adversarial perturbation in input data of the neural network and provides a detection result. Also disclosed is a backend server, a detection device and a system.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyrEKwjAQgOEuDqK-w4Gz0EbR-UwubVAvckkUXEqROIkW6vtjBx9A-OFfvmkRThQbb8B6ASHta3Y3xzUgA5oLSUBxeATjQkyyR9YEjsfOKYLBiOAtIDAlGRVTvHo5zIvJo3sOefH7rFhairpZ5f7d5qHv7vmVP20KqlRVuVFbtcNq_Z_6AqCnMII</recordid><startdate>20210211</startdate><enddate>20210211</enddate><creator>SCHLICHT, Peter</creator><creator>VARGHESE, John Serin</creator><creator>KAPOOR, Nikhil</creator><scope>EVB</scope></search><sort><creationdate>20210211</creationdate><title>METHOD FOR RECOGNIZING AN ADVERSARIAL DISTURBANCE IN INPUT DATA OF A NEURAL NETWORK</title><author>SCHLICHT, Peter ; VARGHESE, John Serin ; KAPOOR, Nikhil</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2021042627A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>SCHLICHT, Peter</creatorcontrib><creatorcontrib>VARGHESE, John Serin</creatorcontrib><creatorcontrib>KAPOOR, Nikhil</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SCHLICHT, Peter</au><au>VARGHESE, John Serin</au><au>KAPOOR, Nikhil</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD FOR RECOGNIZING AN ADVERSARIAL DISTURBANCE IN INPUT DATA OF A NEURAL NETWORK</title><date>2021-02-11</date><risdate>2021</risdate><abstract>A method for detecting an adversarial perturbation in input data of a neural network, wherein a conditional generative adversarial network is trained during a training phase, wherein a generator network of the conditional generative adversarial network is trained to generate adversarial perturbations conditioned on input data of the neural network, and wherein a discriminator network of the conditional generative adversarial network is trained at least to detect an adversarial perturbation in the input data generated by the generator network, and wherein, during an application phase, the trained discriminator network detects an adversarial perturbation in input data of the neural network and provides a detection result. Also disclosed is a backend server, a detection device and a system.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2021042627A1
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
title	METHOD FOR RECOGNIZING AN ADVERSARIAL DISTURBANCE IN INPUT DATA OF A NEURAL NETWORK
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T12%3A28%3A27IST&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=SCHLICHT,%20Peter&rft.date=2021-02-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2021042627A1%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