APPARATUS AND METHOD FOR DETERMINING VULNERABILITY OF DEEP LEARNING MODEL
An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage o...
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 | MUN, Hyun Jun YU, Ji Hyeon YUN, Joo Beom |
| description | An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage of the deep learning model by inputting the input image into the deep learning model, and an inspector configured to detect, based on a prediction result of the deep learning model for a class of the input image and a class of the original image, an error in the prediction result. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2022019675A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2022019675A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2022019675A13</originalsourceid><addsrcrecordid>eNrjZPB0DAhwDHIMCQ1WcPRzUfB1DfHwd1Fw8w9ScHENcQ3y9fTz9HNXCAv18XMNcnTy9PEMiVTwdwNKugYo-Lg6BoGlff1dXH14GFjTEnOKU3mhNDeDsptriLOHbmpBfnxqcUFicmpeakl8aLCRgZGRgaGlmbmpo6ExcaoA5ZcuCA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>APPARATUS AND METHOD FOR DETERMINING VULNERABILITY OF DEEP LEARNING MODEL</title><source>esp@cenet</source><creator>MUN, Hyun Jun ; YU, Ji Hyeon ; YUN, Joo Beom</creator><creatorcontrib>MUN, Hyun Jun ; YU, Ji Hyeon ; YUN, Joo Beom</creatorcontrib><description>An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage of the deep learning model by inputting the input image into the deep learning model, and an inspector configured to detect, based on a prediction result of the deep learning model for a class of the input image and a class of the original image, an error in the prediction result.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</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&date=20220120&DB=EPODOC&CC=US&NR=2022019675A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220120&DB=EPODOC&CC=US&NR=2022019675A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MUN, Hyun Jun</creatorcontrib><creatorcontrib>YU, Ji Hyeon</creatorcontrib><creatorcontrib>YUN, Joo Beom</creatorcontrib><title>APPARATUS AND METHOD FOR DETERMINING VULNERABILITY OF DEEP LEARNING MODEL</title><description>An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage of the deep learning model by inputting the input image into the deep learning model, and an inspector configured to detect, based on a prediction result of the deep learning model for a class of the input image and a class of the original image, an error in the prediction result.</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>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPB0DAhwDHIMCQ1WcPRzUfB1DfHwd1Fw8w9ScHENcQ3y9fTz9HNXCAv18XMNcnTy9PEMiVTwdwNKugYo-Lg6BoGlff1dXH14GFjTEnOKU3mhNDeDsptriLOHbmpBfnxqcUFicmpeakl8aLCRgZGRgaGlmbmpo6ExcaoA5ZcuCA</recordid><startdate>20220120</startdate><enddate>20220120</enddate><creator>MUN, Hyun Jun</creator><creator>YU, Ji Hyeon</creator><creator>YUN, Joo Beom</creator><scope>EVB</scope></search><sort><creationdate>20220120</creationdate><title>APPARATUS AND METHOD FOR DETERMINING VULNERABILITY OF DEEP LEARNING MODEL</title><author>MUN, Hyun Jun ; YU, Ji Hyeon ; YUN, Joo Beom</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2022019675A13</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>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>MUN, Hyun Jun</creatorcontrib><creatorcontrib>YU, Ji Hyeon</creatorcontrib><creatorcontrib>YUN, Joo Beom</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MUN, Hyun Jun</au><au>YU, Ji Hyeon</au><au>YUN, Joo Beom</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>APPARATUS AND METHOD FOR DETERMINING VULNERABILITY OF DEEP LEARNING MODEL</title><date>2022-01-20</date><risdate>2022</risdate><abstract>An apparatus for determining a vulnerability of a deep learning model according to an embodiment includes a converter configured to generate an input image for the deep learning model by transforming an original image selected from an image dataset, a measurer configured to measure neuron coverage of the deep learning model by inputting the input image into the deep learning model, and an inspector configured to detect, based on a prediction result of the deep learning model for a class of the input image and a class of the original image, an error in the prediction result.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2022019675A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | APPARATUS AND METHOD FOR DETERMINING VULNERABILITY OF DEEP LEARNING MODEL |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T00%3A48%3A21IST&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=MUN,%20Hyun%20Jun&rft.date=2022-01-20&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2022019675A1%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 |