Black box confrontation sample generation method and device, equipment and storage medium

The invention discloses a black box confrontation sample generation method and device, equipment and a storage medium, and relates to the technical field of deep learning security, and the method comprises the steps: training an initial target detection model through employing a pre-obtained data se...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: DAI HAORENG, MI JIANXUN, XIANG FEI, ZHONG JIAYONG, ZHAO XIANGJIN, CHEN YONGTAO, LYU XIAOHONG, LI SONGNONG, KUANG PENGYAN, CHENG XIAO, TIAN PENG, PENG WENXIN, XU KAI, JIANG JINYANG, CHEN TAO, LI ZEPING, ZHANG ZHEYU
Format: Patent
Sprache:chi ; 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 DAI HAORENG
MI JIANXUN
XIANG FEI
ZHONG JIAYONG
ZHAO XIANGJIN
CHEN YONGTAO
LYU XIAOHONG
LI SONGNONG
KUANG PENGYAN
CHENG XIAO
TIAN PENG
PENG WENXIN
XU KAI
JIANG JINYANG
CHEN TAO
LI ZEPING
ZHANG ZHEYU
description The invention discloses a black box confrontation sample generation method and device, equipment and a storage medium, and relates to the technical field of deep learning security, and the method comprises the steps: training an initial target detection model through employing a pre-obtained data set, and determining the trained target detection model as a black box target detection model; inputting the target image into a black box target detection model, obtaining a plurality of prediction results, and generating a heat map based on the prediction results and a preset heat map generation algorithm; generating a target mask based on the heat map, generating adversarial disturbance by using a target technology, limiting a disturbance area of the adversarial disturbance by using the target mask, and determining an adversarial sample according to the corresponding limited adversarial disturbance. Therefore, according to the application, the coverage area of the confrontation disturbance can be limited to the ef
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117853846A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117853846A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117853846A3</originalsourceid><addsrcrecordid>eNqNjDEOwjAMALswIOAPZoehKtCuUIGYmFiYKpO4JSKJQ-Iink8FPIDppNPpxtllZ1Hd4covUOzbyF5QDHtI6IIl6MhT_BpHcmMN6DVoehpFC6BHb4IjLx-bhCN2NITa9G6ajVq0iWY_TrL5YX-uj0sK3FAKqIa1NPUpz8tqXVSrzbb4p3kD9yY63w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Black box confrontation sample generation method and device, equipment and storage medium</title><source>esp@cenet</source><creator>DAI HAORENG ; MI JIANXUN ; XIANG FEI ; ZHONG JIAYONG ; ZHAO XIANGJIN ; CHEN YONGTAO ; LYU XIAOHONG ; LI SONGNONG ; KUANG PENGYAN ; CHENG XIAO ; TIAN PENG ; PENG WENXIN ; XU KAI ; JIANG JINYANG ; CHEN TAO ; LI ZEPING ; ZHANG ZHEYU</creator><creatorcontrib>DAI HAORENG ; MI JIANXUN ; XIANG FEI ; ZHONG JIAYONG ; ZHAO XIANGJIN ; CHEN YONGTAO ; LYU XIAOHONG ; LI SONGNONG ; KUANG PENGYAN ; CHENG XIAO ; TIAN PENG ; PENG WENXIN ; XU KAI ; JIANG JINYANG ; CHEN TAO ; LI ZEPING ; ZHANG ZHEYU</creatorcontrib><description>The invention discloses a black box confrontation sample generation method and device, equipment and a storage medium, and relates to the technical field of deep learning security, and the method comprises the steps: training an initial target detection model through employing a pre-obtained data set, and determining the trained target detection model as a black box target detection model; inputting the target image into a black box target detection model, obtaining a plurality of prediction results, and generating a heat map based on the prediction results and a preset heat map generation algorithm; generating a target mask based on the heat map, generating adversarial disturbance by using a target technology, limiting a disturbance area of the adversarial disturbance by using the target mask, and determining an adversarial sample according to the corresponding limited adversarial disturbance. Therefore, according to the application, the coverage area of the confrontation disturbance can be limited to the ef</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</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=20240409&amp;DB=EPODOC&amp;CC=CN&amp;NR=117853846A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76419</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240409&amp;DB=EPODOC&amp;CC=CN&amp;NR=117853846A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DAI HAORENG</creatorcontrib><creatorcontrib>MI JIANXUN</creatorcontrib><creatorcontrib>XIANG FEI</creatorcontrib><creatorcontrib>ZHONG JIAYONG</creatorcontrib><creatorcontrib>ZHAO XIANGJIN</creatorcontrib><creatorcontrib>CHEN YONGTAO</creatorcontrib><creatorcontrib>LYU XIAOHONG</creatorcontrib><creatorcontrib>LI SONGNONG</creatorcontrib><creatorcontrib>KUANG PENGYAN</creatorcontrib><creatorcontrib>CHENG XIAO</creatorcontrib><creatorcontrib>TIAN PENG</creatorcontrib><creatorcontrib>PENG WENXIN</creatorcontrib><creatorcontrib>XU KAI</creatorcontrib><creatorcontrib>JIANG JINYANG</creatorcontrib><creatorcontrib>CHEN TAO</creatorcontrib><creatorcontrib>LI ZEPING</creatorcontrib><creatorcontrib>ZHANG ZHEYU</creatorcontrib><title>Black box confrontation sample generation method and device, equipment and storage medium</title><description>The invention discloses a black box confrontation sample generation method and device, equipment and a storage medium, and relates to the technical field of deep learning security, and the method comprises the steps: training an initial target detection model through employing a pre-obtained data set, and determining the trained target detection model as a black box target detection model; inputting the target image into a black box target detection model, obtaining a plurality of prediction results, and generating a heat map based on the prediction results and a preset heat map generation algorithm; generating a target mask based on the heat map, generating adversarial disturbance by using a target technology, limiting a disturbance area of the adversarial disturbance by using the target mask, and determining an adversarial sample according to the corresponding limited adversarial disturbance. Therefore, according to the application, the coverage area of the confrontation disturbance can be limited to the ef</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjDEOwjAMALswIOAPZoehKtCuUIGYmFiYKpO4JSKJQ-Iink8FPIDppNPpxtllZ1Hd4covUOzbyF5QDHtI6IIl6MhT_BpHcmMN6DVoehpFC6BHb4IjLx-bhCN2NITa9G6ajVq0iWY_TrL5YX-uj0sK3FAKqIa1NPUpz8tqXVSrzbb4p3kD9yY63w</recordid><startdate>20240409</startdate><enddate>20240409</enddate><creator>DAI HAORENG</creator><creator>MI JIANXUN</creator><creator>XIANG FEI</creator><creator>ZHONG JIAYONG</creator><creator>ZHAO XIANGJIN</creator><creator>CHEN YONGTAO</creator><creator>LYU XIAOHONG</creator><creator>LI SONGNONG</creator><creator>KUANG PENGYAN</creator><creator>CHENG XIAO</creator><creator>TIAN PENG</creator><creator>PENG WENXIN</creator><creator>XU KAI</creator><creator>JIANG JINYANG</creator><creator>CHEN TAO</creator><creator>LI ZEPING</creator><creator>ZHANG ZHEYU</creator><scope>EVB</scope></search><sort><creationdate>20240409</creationdate><title>Black box confrontation sample generation method and device, equipment and storage medium</title><author>DAI HAORENG ; MI JIANXUN ; XIANG FEI ; ZHONG JIAYONG ; ZHAO XIANGJIN ; CHEN YONGTAO ; LYU XIAOHONG ; LI SONGNONG ; KUANG PENGYAN ; CHENG XIAO ; TIAN PENG ; PENG WENXIN ; XU KAI ; JIANG JINYANG ; CHEN TAO ; LI ZEPING ; ZHANG ZHEYU</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117853846A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</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>DAI HAORENG</creatorcontrib><creatorcontrib>MI JIANXUN</creatorcontrib><creatorcontrib>XIANG FEI</creatorcontrib><creatorcontrib>ZHONG JIAYONG</creatorcontrib><creatorcontrib>ZHAO XIANGJIN</creatorcontrib><creatorcontrib>CHEN YONGTAO</creatorcontrib><creatorcontrib>LYU XIAOHONG</creatorcontrib><creatorcontrib>LI SONGNONG</creatorcontrib><creatorcontrib>KUANG PENGYAN</creatorcontrib><creatorcontrib>CHENG XIAO</creatorcontrib><creatorcontrib>TIAN PENG</creatorcontrib><creatorcontrib>PENG WENXIN</creatorcontrib><creatorcontrib>XU KAI</creatorcontrib><creatorcontrib>JIANG JINYANG</creatorcontrib><creatorcontrib>CHEN TAO</creatorcontrib><creatorcontrib>LI ZEPING</creatorcontrib><creatorcontrib>ZHANG ZHEYU</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DAI HAORENG</au><au>MI JIANXUN</au><au>XIANG FEI</au><au>ZHONG JIAYONG</au><au>ZHAO XIANGJIN</au><au>CHEN YONGTAO</au><au>LYU XIAOHONG</au><au>LI SONGNONG</au><au>KUANG PENGYAN</au><au>CHENG XIAO</au><au>TIAN PENG</au><au>PENG WENXIN</au><au>XU KAI</au><au>JIANG JINYANG</au><au>CHEN TAO</au><au>LI ZEPING</au><au>ZHANG ZHEYU</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Black box confrontation sample generation method and device, equipment and storage medium</title><date>2024-04-09</date><risdate>2024</risdate><abstract>The invention discloses a black box confrontation sample generation method and device, equipment and a storage medium, and relates to the technical field of deep learning security, and the method comprises the steps: training an initial target detection model through employing a pre-obtained data set, and determining the trained target detection model as a black box target detection model; inputting the target image into a black box target detection model, obtaining a plurality of prediction results, and generating a heat map based on the prediction results and a preset heat map generation algorithm; generating a target mask based on the heat map, generating adversarial disturbance by using a target technology, limiting a disturbance area of the adversarial disturbance by using the target mask, and determining an adversarial sample according to the corresponding limited adversarial disturbance. Therefore, according to the application, the coverage area of the confrontation disturbance can be limited to the ef</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117853846A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Black box confrontation sample generation method and device, equipment and storage medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T02%3A26%3A36IST&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=DAI%20HAORENG&rft.date=2024-04-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117853846A%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