Black box video confrontation sample generation method and evaluation method based on reinforcement learning
The invention discloses a black box video adversarial sample generation method based on reinforcement learning. The method comprises the following steps: acquiring original video data and segmenting the original video data to obtain a video block set; inserting position information into the video bl...
Saved in:
Main Authors | , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
08.11.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The invention discloses a black box video adversarial sample generation method based on reinforcement learning. The method comprises the following steps: acquiring original video data and segmenting the original video data to obtain a video block set; inserting position information into the video block set to obtain the video block set with the position information; performing visual feature extraction to obtain features of the video blocks; extracting the video block set with the position information to obtain a key video block set; iterating the key video block set to obtain an estimation gradient; generating a confrontation sample value and constructing a corresponding loss function; and inputting the confrontation sample value into the target video model to obtain a return value, and obtaining a finally constructed confrontation sample according to the return value and the loss function value. The invention further discloses an evaluation method comprising the black box video confrontation sample generati |
---|---|
AbstractList | The invention discloses a black box video adversarial sample generation method based on reinforcement learning. The method comprises the following steps: acquiring original video data and segmenting the original video data to obtain a video block set; inserting position information into the video block set to obtain the video block set with the position information; performing visual feature extraction to obtain features of the video blocks; extracting the video block set with the position information to obtain a key video block set; iterating the key video block set to obtain an estimation gradient; generating a confrontation sample value and constructing a corresponding loss function; and inputting the confrontation sample value into the target video model to obtain a return value, and obtaining a finally constructed confrontation sample according to the return value and the loss function value. The invention further discloses an evaluation method comprising the black box video confrontation sample generati |
Author | YU RUISHI ZHAN YU HU CHAO LIU RONGKAI SHI HEYUAN LIANG KAI |
Author_xml | – fullname: LIANG KAI – fullname: LIU RONGKAI – fullname: HU CHAO – fullname: SHI HEYUAN – fullname: ZHAN YU – fullname: YU RUISHI |
BookMark | eNqNjTsOwjAQRF1Awe8OywEoQsQBIAJRUdFHG3sCFs5uZJuI4xMJGjqK0dM8jTRzMxEVzEw4BLYPavRFg3dQsiptVMmcvQol7voAukEQP6ZDvqsjFkcYODx_bMMJjsYe4aXVaNFBMgVwFC-3pZm2HBJWXy7M-nS8VucNeq2RerbjT66rS1HsyjHbYl_-s3kDzZ5EEg |
ContentType | Patent |
DBID | EVB |
DatabaseName | esp@cenet |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Chemistry Sciences Physics |
DocumentTitleAlternate | 基于强化学习的黑盒视频对抗样本生成方法及评价方法 |
ExternalDocumentID | CN115311521A |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_CN115311521A3 |
IEDL.DBID | EVB |
IngestDate | Fri Jul 19 14:35:43 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | Chinese English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_CN115311521A3 |
Notes | Application Number: CN202211111492 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221108&DB=EPODOC&CC=CN&NR=115311521A |
ParticipantIDs | epo_espacenet_CN115311521A |
PublicationCentury | 2000 |
PublicationDate | 20221108 |
PublicationDateYYYYMMDD | 2022-11-08 |
PublicationDate_xml | – month: 11 year: 2022 text: 20221108 day: 08 |
PublicationDecade | 2020 |
PublicationYear | 2022 |
RelatedCompanies | CENTRAL SOUTH UNIVERSITY |
RelatedCompanies_xml | – name: CENTRAL SOUTH UNIVERSITY |
Score | 3.5631628 |
Snippet | The invention discloses a black box video adversarial sample generation method based on reinforcement learning. The method comprises the following steps:... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTING COUNTING PHYSICS |
Title | Black box video confrontation sample generation method and evaluation method based on reinforcement learning |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221108&DB=EPODOC&locale=&CC=CN&NR=115311521A |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NS8NAEB1q_bxpVbR-sILkFmyT1OQSxG4SitC0SJXeSnaTVEWS0kQUf72zY2K96DETWLIDs7PvZeYNwKXZlallRghTDWHqlkjxHDTSRLds24nNKI2kUHzHMLwePFh30960AS91LwzphL6TOCJGlMR4L-m8XqxILI9qK4sr8Yym_CaYuJ5WoWNDwRlH8_quPx55I65x7vJQC-9dvPgoXRmje7sG63iNdlT5n__YV10pi98pJdiFjTGulpV70Ph8asE2ryevtWBrWP3wbsEmVWjKAo1VFBb78EqsGxP5B1NddDlDTJsqIQL6cFZESvGXzUlQmizfY6JZlMVspe5dW1Ueixk-LxNSUZVEGLJqnMT8AC4Cf8IHOm5g9uOtGQ9XezUPoZnlWXIELHKk7MhUYDqXivYRHdkz7G7cEYgoEBMdQ_vvddr_vTyBHeV5atBzTqFZLt-SM8zUpTgnF38BWC2aFA |
link.rule.ids | 230,309,786,891,25585,76894 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8JAEJ4gPvCmKFF8rYnpjUgfSD00RrYQVCjEoOFGutsWNaYltEbjr3d2LOJFj50mm31kdvb7ducbgDNTl5Fl-ghTDWHWLBHhPmhEYc1qNu3A9CNfCsV39L2L7oN1O26MC_CyyIUhndB3EkdEj5Lo7xnt17MlieXS28r0XDyjKbnqjBxXy9GxoeCMrbktpz0cuAOuce5wT_PuHTz4KF0ZQ79egVU8Yl8qnf32Y0tlpcx-h5TOFqwNsbU424bC51MZSnxRea0MG_38wrsM6_RCU6ZozL0w3YFXYt2YSD6YyqJLGGLaSAkRUMdZ6ivFXzYlQWmyfJeJZn4csKW698Kq4ljA8HsekoqqJMKQ5eUkprtw2mmPeLeGA5j8zNaEe8uxmhUoxkkc7gHzbSnrMhIYzqWifURdNoymHtQFIgrERPtQ_bud6n8_T6DUHfV7k96Nd3cAm2oVKFnPPoRiNn8LjzBqZ-KYpvsLv5CdBw |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Black+box+video+confrontation+sample+generation+method+and+evaluation+method+based+on+reinforcement+learning&rft.inventor=LIANG+KAI&rft.inventor=LIU+RONGKAI&rft.inventor=HU+CHAO&rft.inventor=SHI+HEYUAN&rft.inventor=ZHAN+YU&rft.inventor=YU+RUISHI&rft.date=2022-11-08&rft.externalDBID=A&rft.externalDocID=CN115311521A |