{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T06:03:16Z","timestamp":1780984996688,"version":"3.54.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia"},{"name":"Researchers Supporting Project","award":["PNURSP2025R333"],"award-info":[{"award-number":["PNURSP2025R333"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tce.2025.3643172","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:45:23Z","timestamp":1765478723000},"page":"5177-5186","source":"Crossref","is-referenced-by-count":0,"title":["A Secure Multimodal Retrieval Framework for Consumer Electronics Under AI-Driven Attacks"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0175-8660","authenticated-orcid":false,"given":"Guodong","family":"Wang","sequence":"first","affiliation":[{"name":"Shandong Xiehe University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Anhui University of Finance and Economics, Bengbu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0455-8086","authenticated-orcid":false,"given":"Luo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Donghua University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asma Hassan","family":"Alshehri","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1420-8163","authenticated-orcid":false,"given":"Wenhao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Transportation, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3385440"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3665348.3665381"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2025.3640136"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2025.3640136"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT61001.2024.11422457"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2024.3387049"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3368206"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113392"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref10","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref11","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111211"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02769"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3883"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-023-01249-w"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tccn.2025.3577323"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369656"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446511"},{"key":"ref19","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00824-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3417694"},{"key":"ref24","first-page":"9774","article-title":"TriBERT: Human-centric audio-visual representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Rahman"},{"key":"ref25","first-page":"285","article-title":"GRAVL-BERT: Graphical visual-linguistic representations for multimodal coreference resolution","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Guo"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109272"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00108"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref29","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andrew"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749341"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3152086"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00585"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18293\/DMS2015-005"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331213"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548066"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref39","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00473"},{"key":"ref43","first-page":"4974","article-title":"A simple neural network module for relational reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santoro"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3572827"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11553428\/11298154.pdf?arnumber=11298154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T05:42:49Z","timestamp":1780983769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11298154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":49,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3643172","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}