A User-Centric Context-Aware Framework for Real-Time Optimisation of Multimedia Data Privacy Protection, and Information Retention Within Multimodal AI Systems

The increasing use of AI systems for face, object, action, scene, and emotion recognition raises significant privacy risks, particularly when processing Personally Identifiable Information (PII). Current privacy-preserving methods lack adaptability to users’ preferences and contextual requirements,...

Full description

Saved in:

Bibliographic Details
Published in:	Sensors (Basel, Switzerland) Vol. 25; no. 19; p. 6105
Main Authors:	Topalli, Ndricim, Badii, Atta
Format:	Journal Article
Language:	English
Published:	Switzerland MDPI AG 03.10.2025
Subjects:	Algorithms Artificial Intelligence Biometrics Biometry Compliance Computer Security Data integrity data intelligibility Decision making Facial recognition technology hard biometrics Humans Machine learning Multimedia multimodal data Ontology Privacy privacy engineering Privacy, Right of re-identification Semantics soft biometrics Usability User behavior privacy protection dynamic privacy adaptation privacy engineering data intelligibility real-time data obfuscation re-identification user-centric privacy context-aware AI hard biometrics multimodal data GDPR compliance soft biometrics
ISSN:	1424-8220, 1424-8220
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	The increasing use of AI systems for face, object, action, scene, and emotion recognition raises significant privacy risks, particularly when processing Personally Identifiable Information (PII). Current privacy-preserving methods lack adaptability to users’ preferences and contextual requirements, and obfuscate user faces uniformly. This research proposes a user-centric, context-aware, and ontology-driven privacy protection framework that dynamically adjusts privacy decisions based on user-defined preferences, entity sensitivity, and contextual information. The framework integrates state-of-the-art recognition models for recognising faces, objects, scenes, actions, and emotions in real time on data acquired from vision sensors (e.g., cameras). Privacy decisions are directed by a contextual ontology based in Contextual Integrity theory, which classifies entities into private, semi-private, or public categories. Adaptive privacy levels are enforced through obfuscation techniques and a multi-level privacy model that supports user-defined red lines (e.g., “always hide logos”). The framework also proposes a Re-Identifiability Index (RII) using soft biometric features such as gait, hairstyle, clothing, skin tone, age, and gender, to mitigate identity leakage and to support fallback protection when face recognition fails. The experimental evaluation relied on sensor-captured datasets, which replicate real-world image sensors such as surveillance cameras. User studies confirmed that the framework was effective, with over 85.2% of participants rating the obfuscation operations as highly effective, and the other 14.8% stating that obfuscation was adequately effective. Amongst these, 71.4% considered the balance between privacy protection and usability very satisfactory and 28% found it satisfactory. GPU acceleration was deployed to enable real-time performance of these models by reducing frame processing time from 1200 ms (CPU) to 198 ms. This ontology-driven framework employs user-defined red lines, contextual reasoning, and dual metrics (RII/IVI) to dynamically balance privacy protection with scene intelligibility. Unlike current anonymisation methods, the framework provides a real-time, user-centric, and GDPR-compliant method that operationalises privacy-by-design while preserving scene intelligibility. These features make the framework appropriate to a variety of real-world applications including healthcare, surveillance, and social media.
AbstractList	The increasing use of AI systems for face, object, action, scene, and emotion recognition raises significant privacy risks, particularly when processing Personally Identifiable Information (PII). Current privacy-preserving methods lack adaptability to users' preferences and contextual requirements, and obfuscate user faces uniformly. This research proposes a user-centric, context-aware, and ontology-driven privacy protection framework that dynamically adjusts privacy decisions based on user-defined preferences, entity sensitivity, and contextual information. The framework integrates state-of-the-art recognition models for recognising faces, objects, scenes, actions, and emotions in real time on data acquired from vision sensors (e.g., cameras). Privacy decisions are directed by a contextual ontology based in Contextual Integrity theory, which classifies entities into private, semi-private, or public categories. Adaptive privacy levels are enforced through obfuscation techniques and a multi-level privacy model that supports user-defined red lines (e.g., "always hide logos"). The framework also proposes a Re-Identifiability Index (RII) using soft biometric features such as gait, hairstyle, clothing, skin tone, age, and gender, to mitigate identity leakage and to support fallback protection when face recognition fails. The experimental evaluation relied on sensor-captured datasets, which replicate real-world image sensors such as surveillance cameras. User studies confirmed that the framework was effective, with over 85.2% of participants rating the obfuscation operations as highly effective, and the other 14.8% stating that obfuscation was adequately effective. Amongst these, 71.4% considered the balance between privacy protection and usability very satisfactory and 28% found it satisfactory. GPU acceleration was deployed to enable real-time performance of these models by reducing frame processing time from 1200 ms (CPU) to 198 ms. This ontology-driven framework employs user-defined red lines, contextual reasoning, and dual metrics (RII/IVI) to dynamically balance privacy protection with scene intelligibility. Unlike current anonymisation methods, the framework provides a real-time, user-centric, and GDPR-compliant method that operationalises privacy-by-design while preserving scene intelligibility. These features make the framework appropriate to a variety of real-world applications including healthcare, surveillance, and social media. The increasing use of AI systems for face, object, action, scene, and emotion recognition raises significant privacy risks, particularly when processing Personally Identifiable Information (PII). Current privacy-preserving methods lack adaptability to users' preferences and contextual requirements, and obfuscate user faces uniformly. This research proposes a user-centric, context-aware, and ontology-driven privacy protection framework that dynamically adjusts privacy decisions based on user-defined preferences, entity sensitivity, and contextual information. The framework integrates state-of-the-art recognition models for recognising faces, objects, scenes, actions, and emotions in real time on data acquired from vision sensors (e.g., cameras). Privacy decisions are directed by a contextual ontology based in Contextual Integrity theory, which classifies entities into private, semi-private, or public categories. Adaptive privacy levels are enforced through obfuscation techniques and a multi-level privacy model that supports user-defined red lines (e.g., "always hide logos"). The framework also proposes a Re-Identifiability Index (RII) using soft biometric features such as gait, hairstyle, clothing, skin tone, age, and gender, to mitigate identity leakage and to support fallback protection when face recognition fails. The experimental evaluation relied on sensor-captured datasets, which replicate real-world image sensors such as surveillance cameras. User studies confirmed that the framework was effective, with over 85.2% of participants rating the obfuscation operations as highly effective, and the other 14.8% stating that obfuscation was adequately effective. Amongst these, 71.4% considered the balance between privacy protection and usability very satisfactory and 28% found it satisfactory. GPU acceleration was deployed to enable real-time performance of these models by reducing frame processing time from 1200 ms (CPU) to 198 ms. This ontology-driven framework employs user-defined red lines, contextual reasoning, and dual metrics (RII/IVI) to dynamically balance privacy protection with scene intelligibility. Unlike current anonymisation methods, the framework provides a real-time, user-centric, and GDPR-compliant method that operationalises privacy-by-design while preserving scene intelligibility. These features make the framework appropriate to a variety of real-world applications including healthcare, surveillance, and social media.The increasing use of AI systems for face, object, action, scene, and emotion recognition raises significant privacy risks, particularly when processing Personally Identifiable Information (PII). Current privacy-preserving methods lack adaptability to users' preferences and contextual requirements, and obfuscate user faces uniformly. This research proposes a user-centric, context-aware, and ontology-driven privacy protection framework that dynamically adjusts privacy decisions based on user-defined preferences, entity sensitivity, and contextual information. The framework integrates state-of-the-art recognition models for recognising faces, objects, scenes, actions, and emotions in real time on data acquired from vision sensors (e.g., cameras). Privacy decisions are directed by a contextual ontology based in Contextual Integrity theory, which classifies entities into private, semi-private, or public categories. Adaptive privacy levels are enforced through obfuscation techniques and a multi-level privacy model that supports user-defined red lines (e.g., "always hide logos"). The framework also proposes a Re-Identifiability Index (RII) using soft biometric features such as gait, hairstyle, clothing, skin tone, age, and gender, to mitigate identity leakage and to support fallback protection when face recognition fails. The experimental evaluation relied on sensor-captured datasets, which replicate real-world image sensors such as surveillance cameras. User studies confirmed that the framework was effective, with over 85.2% of participants rating the obfuscation operations as highly effective, and the other 14.8% stating that obfuscation was adequately effective. Amongst these, 71.4% considered the balance between privacy protection and usability very satisfactory and 28% found it satisfactory. GPU acceleration was deployed to enable real-time performance of these models by reducing frame processing time from 1200 ms (CPU) to 198 ms. This ontology-driven framework employs user-defined red lines, contextual reasoning, and dual metrics (RII/IVI) to dynamically balance privacy protection with scene intelligibility. Unlike current anonymisation methods, the framework provides a real-time, user-centric, and GDPR-compliant method that operationalises privacy-by-design while preserving scene intelligibility. These features make the framework appropriate to a variety of real-world applications including healthcare, surveillance, and social media.
Audience	Academic
Author	Topalli, Ndricim Badii, Atta
Author_xml	– sequence: 1 givenname: Ndricim orcidid: 0009-0009-4238-4253 surname: Topalli fullname: Topalli, Ndricim – sequence: 2 givenname: Atta surname: Badii fullname: Badii, Atta
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/41094928$$D View this record in MEDLINE/PubMed
BookMark	eNpdks1u1DAQxyNURD_gwAsgS1xAIsWOHcc-rhYKKxUVlVYco4kzLl6SeLG9lH0aXhVvd1khNIcZjX7zH83HaXE0-QmL4jmj55xr-jZWNdOS0fpRccJEJUpVVfTon_i4OI1xSWnFOVdPimPBqBa6UifF7xm5jRjKOU4pOEPmfkr4K5WzewhILgKMeO_Dd2J9INcIQ3njRiRXq-RGFyE5PxFvyaf1kBPYOyDvIAH5HNxPMJvsfUKzpd4QmHqymLLOuCu7xpR7bqOvLn1z017E9zCQ2YJ82cSEY3xaPLYwRHy292fF7cX7m_nH8vLqw2I-uyyNYHUqtWANNNBTqypNe6N1h7qxUhsqEWQjBNaoQcmusrVGMNh0llklLFWN1YqfFYudbu9h2a6CGyFsWg-ufUj4cNdCSM4M2DKwtu-U6DhjAqlSShrTSSpNXjVHlrVe7bRWwf9YY0xt3pXBYYAJ_Tq2vJKs0UIqkdGX_6FLvw5TnvSBoppSuRU831F3kPu7vMQUwGTrcXQm_4J1OT9TsmI1p3xb8GIvu-7yWQ7z_L17Bl7vABN8jAHtAWG03f5Ue_gp_gfzGL2s
Cites_doi	10.1109/SP.2009.22 10.1109/ISBA.2016.7477240 10.1109/JIOT.2017.2773600 10.1109/SP.2017.25 10.1109/TIFS.2015.2480381 10.1038/s41591-021-01343-4 10.5220/0005126603410345 10.1007/978-3-030-32583-1_2 10.1109/ICCV.2017.324 10.1109/ICCV.2009.5459413 10.1109/CVPR.2017.365 10.3390/app14156824 10.1007/978-3-319-46448-0_2 10.1145/3394171.3413972 10.1109/FG.2018.00020 10.3390/s21113845 10.1109/SPW.2015.13 10.5244/C.29.41 10.1109/TKDE.2005.32 10.1515/9780804772891 10.1007/978-3-319-46487-9_6 10.1109/CVPR.2019.00482 10.3390/su13031224 10.1016/j.physd.2019.132306 10.1109/ACCESS.2019.2952065 10.1038/nature14539 10.1109/CVPR.2014.220 10.1016/j.jnca.2023.103695 10.1109/ICCV.2017.322 10.1109/ACCESS.2020.2978223 10.1109/ICCV.2019.00667 10.1109/CVPR42600.2020.01079 10.1007/978-3-030-01246-5_38 10.1109/CVPRW.2017.175 10.1145/3357375 10.1109/CVPR.2017.502 10.1109/IWSSIP.2015.7314228 10.1186/s13640-015-0078-1 10.1145/2976749.2978318 10.1109/CVPR.2015.7298682 10.1109/MMSP.2012.6343470 10.1007/s11042-010-0635-7 10.1145/3561048 10.1007/978-3-319-10602-1_48 10.1109/ICCV.2015.169 10.1080/1369118X.2013.777757 10.1016/j.cose.2015.07.002 10.3115/v1/D14-1179 10.1109/CVPR.2016.90 10.1109/TPAMI.2016.2577031
ContentType	Journal Article
Copyright	COPYRIGHT 2025 MDPI AG 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: COPYRIGHT 2025 MDPI AG – notice: 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 3V. 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 DOA
DOI	10.3390/s25196105
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) ProQuest Databases ProQuest One Academic Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	MEDLINE Publicly Available Content Database MEDLINE - Academic CrossRef
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1424-8220
ExternalDocumentID	oai_doaj_org_article_1affdb84b3114e08886ccb606c8223e1 A862153031 41094928 10_3390_s25196105
Genre	Journal Article
GroupedDBID	--- 123 2WC 53G 5VS 7X7 88E 8FE 8FG 8FI 8FJ AADQD AAHBH AAYXX ABDBF ABUWG ACUHS ADBBV ADMLS AENEX AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS BENPR BPHCQ BVXVI CCPQU CITATION CS3 D1I DU5 E3Z EBD ESX F5P FYUFA GROUPED_DOAJ GX1 HH5 HMCUK HYE IAO ITC KQ8 L6V M1P MODMG M~E OK1 OVT P2P P62 PHGZM PHGZT PIMPY PJZUB PPXIY PQQKQ PROAC PSQYO RNS RPM TUS UKHRP XSB ~8M CGR CUY CVF ECM EIF NPM 3V. 7XB 8FK AZQEC DWQXO K9. M48 PKEHL PQEST PQUKI PRINS 7X8
ID	FETCH-LOGICAL-c415t-9417a7ad0f8290dc99be97f69c06ea6744e5e9a86b2f59eace7bf1f84f087f983
IEDL.DBID	DOA
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001593938200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1424-8220
IngestDate	Mon Oct 20 20:02:56 EDT 2025 Sat Oct 18 22:53:46 EDT 2025 Sat Nov 29 14:29:22 EST 2025 Tue Nov 04 05:01:29 EST 2025 Fri Nov 28 01:41:36 EST 2025 Thu Nov 20 00:53:18 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	19
Keywords	privacy protection dynamic privacy adaptation privacy engineering data intelligibility real-time data obfuscation re-identification user-centric privacy context-aware AI hard biometrics multimodal data GDPR compliance soft biometrics
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c415t-9417a7ad0f8290dc99be97f69c06ea6744e5e9a86b2f59eace7bf1f84f087f983
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0009-0009-4238-4253
OpenAccessLink	https://doaj.org/article/1affdb84b3114e08886ccb606c8223e1
PMID	41094928
PQID	3261090061
PQPubID	2032333
ParticipantIDs	doaj_primary_oai_doaj_org_article_1affdb84b3114e08886ccb606c8223e1 proquest_miscellaneous_3261794684 proquest_journals_3261090061 gale_infotracacademiconefile_A862153031 pubmed_primary_41094928 crossref_primary_10_3390_s25196105
PublicationCentury	2000
PublicationDate	2025-10-03
PublicationDateYYYYMMDD	2025-10-03
PublicationDate_xml	– month: 10 year: 2025 text: 2025-10-03 day: 03
PublicationDecade	2020
PublicationPlace	Switzerland
PublicationPlace_xml	– name: Switzerland – name: Basel
PublicationTitle	Sensors (Basel, Switzerland)
PublicationTitleAlternate	Sensors (Basel)
PublicationYear	2025
Publisher	MDPI AG
Publisher_xml	– name: MDPI AG
References	Dantcheva (ref_38) 2011; 51 ref_14 ref_58 ref_13 ref_12 ref_56 ref_55 ref_10 ref_54 ref_53 ref_52 ref_51 Troncoso (ref_26) 2011; 14 LeCun (ref_76) 2015; 521 ref_19 ref_17 Bari (ref_18) 2019; 7 Newton (ref_15) 2005; 17 Moctezuma (ref_34) 2015; 2015 ref_61 Young (ref_46) 2015; 16 ref_69 ref_24 ref_68 ref_23 ref_67 ref_22 ref_66 ref_21 ref_65 ref_20 ref_64 ref_63 ref_29 ref_28 Liu (ref_1) 2020; 54 Huang (ref_74) 2020; 8 ref_72 ref_71 ref_70 Jiang (ref_2) 2021; 54 ref_35 ref_33 ref_77 ref_32 Wang (ref_48) 2020; 9 ref_31 ref_75 ref_30 ref_73 Krizhevsky (ref_59) 2012; 25 Zhang (ref_57) 2022; 23 ref_39 Ren (ref_60) 2016; 39 Rivadeneira (ref_16) 2023; 217 Kokolakis (ref_4) 2017; 64 ref_47 Badii (ref_11) 2013; 4 ref_45 ref_44 ref_43 ref_42 ref_41 Litjens (ref_36) 2021; 27 ref_40 ref_3 Sherstinsky (ref_62) 2020; 404 ref_49 Dwivedi (ref_50) 2023; 55 ref_9 ref_8 Dantcheva (ref_37) 2015; 11 ref_5 Fierrez (ref_25) 2018; 3 Sezer (ref_27) 2018; 5 ref_7 ref_6 41305309 - Sensors (Basel). 2025 Nov 14;25(22):6957. doi: 10.3390/s25226957.
References_xml	– ident: ref_24 doi: 10.1109/SP.2009.22 – volume: 54 start-page: 1 year: 2021 ident: ref_2 article-title: Location Privacy-preserving Mechanisms in Location-based Services: A Comprehensive Survey publication-title: ACM Comput. Surv. – ident: ref_5 – ident: ref_19 doi: 10.1109/ISBA.2016.7477240 – ident: ref_68 – volume: 5 start-page: 1 year: 2018 ident: ref_27 article-title: Context-Aware Computing, Learning, and Big Data in Internet of Things: A Survey publication-title: IEEE Internet Things J. doi: 10.1109/JIOT.2017.2773600 – ident: ref_22 doi: 10.1109/SP.2017.25 – volume: 3 start-page: 2001 year: 2018 ident: ref_25 article-title: Facial Soft Biometrics for Recognition in the Wild Recent Works, Annotations and COTS Evaluation publication-title: IEEE Trans. Inf. Forensics Secur. – volume: 11 start-page: 441 year: 2015 ident: ref_37 article-title: What Else Your Biometric Data Reveal? A Survey on Soft Biometrics publication-title: IEEE Trans. Inf. Forensics Secur. doi: 10.1109/TIFS.2015.2480381 – volume: 27 start-page: 775 year: 2021 ident: ref_36 article-title: Deep learning in histopathology: The path to the clinic publication-title: Nat. Med. doi: 10.1038/s41591-021-01343-4 – ident: ref_13 doi: 10.5220/0005126603410345 – ident: ref_20 doi: 10.1007/978-3-030-32583-1_2 – ident: ref_64 doi: 10.1109/ICCV.2017.324 – ident: ref_8 doi: 10.1109/ICCV.2009.5459413 – ident: ref_71 doi: 10.1109/CVPR.2017.365 – ident: ref_42 – ident: ref_35 – ident: ref_23 – ident: ref_58 – ident: ref_32 doi: 10.3390/app14156824 – volume: 14 start-page: 25 year: 2011 ident: ref_26 article-title: Engineering Privacy by Design publication-title: Comput. Priv. Data Prot. – ident: ref_63 doi: 10.1007/978-3-319-46448-0_2 – ident: ref_14 doi: 10.1145/3394171.3413972 – ident: ref_40 doi: 10.1109/FG.2018.00020 – ident: ref_56 – volume: 25 start-page: 1097 year: 2012 ident: ref_59 article-title: ImageNet Classification with Deep Convolutional Neural Networks publication-title: Adv. Neural Inf. Process. Syst. – ident: ref_69 – volume: 4 start-page: 13 year: 2013 ident: ref_11 article-title: Holistic Privacy Impact Assessment Framework for Video Privacy Filtering Technologies publication-title: Signal Image Process. Int. J. – ident: ref_70 doi: 10.3390/s21113845 – ident: ref_6 doi: 10.1109/SPW.2015.13 – ident: ref_45 – ident: ref_72 – ident: ref_54 doi: 10.5244/C.29.41 – volume: 17 start-page: 232 year: 2005 ident: ref_15 article-title: Preserving privacy by de-identifying face images publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2005.32 – ident: ref_17 doi: 10.1515/9780804772891 – ident: ref_28 doi: 10.1007/978-3-319-46487-9_6 – ident: ref_55 doi: 10.1109/CVPR.2019.00482 – ident: ref_29 doi: 10.3390/su13031224 – volume: 404 start-page: 132306 year: 2020 ident: ref_62 article-title: Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network publication-title: Phys. D Nonlinear Phenom. doi: 10.1016/j.physd.2019.132306 – ident: ref_7 – volume: 7 start-page: 162708 year: 2019 ident: ref_18 article-title: Artificial Neural Network Based Gait Recognition Using Kinect Sensor publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2952065 – volume: 521 start-page: 436 year: 2015 ident: ref_76 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – ident: ref_52 doi: 10.1109/CVPR.2014.220 – ident: ref_30 – volume: 217 start-page: 103695 year: 2023 ident: ref_16 article-title: User-centric privacy preserving models for a new era of the Internet of Things publication-title: J. Netw. Comput. Appl. doi: 10.1016/j.jnca.2023.103695 – ident: ref_3 – ident: ref_47 – ident: ref_61 doi: 10.1109/ICCV.2017.322 – volume: 8 start-page: 45753 year: 2020 ident: ref_74 article-title: Efficient Parallel Inflated Convolution Architecture for Action Recognition publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2978223 – ident: ref_65 doi: 10.1109/ICCV.2019.00667 – ident: ref_66 doi: 10.1109/CVPR42600.2020.01079 – ident: ref_10 doi: 10.1007/978-3-030-01246-5_38 – ident: ref_9 doi: 10.1109/CVPRW.2017.175 – ident: ref_44 – ident: ref_21 – ident: ref_73 – volume: 54 start-page: 1 year: 2020 ident: ref_1 article-title: When Machine Learning Meets Privacy: A Survey and Outlook publication-title: ACM Comput. Surv. doi: 10.1145/3357375 – ident: ref_43 doi: 10.1109/CVPR.2017.502 – ident: ref_75 – ident: ref_39 doi: 10.1109/IWSSIP.2015.7314228 – volume: 2015 start-page: 28 year: 2015 ident: ref_34 article-title: Soft-biometrics evaluation for people re-identification in uncontrolled multi-camera environments publication-title: EURASIP J. Image Video Process. doi: 10.1186/s13640-015-0078-1 – ident: ref_33 – ident: ref_49 doi: 10.1145/2976749.2978318 – ident: ref_51 doi: 10.1109/CVPR.2015.7298682 – ident: ref_12 – ident: ref_31 doi: 10.1109/MMSP.2012.6343470 – volume: 51 start-page: 739 year: 2011 ident: ref_38 article-title: Bag of soft biometrics for person identification: New trends and challenges publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-010-0635-7 – volume: 55 start-page: 1 year: 2023 ident: ref_50 article-title: Explainable AI (XAI): Core Ideas, Techniques and Solutions publication-title: CM Comput. Surv. doi: 10.1145/3561048 – ident: ref_41 doi: 10.1007/978-3-319-10602-1_48 – volume: 9 start-page: 215 year: 2020 ident: ref_48 article-title: Deep Face Recognition: A Survey publication-title: Neurocomputing – ident: ref_67 doi: 10.1109/ICCV.2015.169 – volume: 16 start-page: 479 year: 2015 ident: ref_46 article-title: Privacy protection strategies on facebook: The internet privacy paradox publication-title: Inf. Commun. Soc. doi: 10.1080/1369118X.2013.777757 – volume: 23 start-page: 499 year: 2022 ident: ref_57 article-title: Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks publication-title: IEEE Signal Process. Lett. – volume: 64 start-page: 122 year: 2017 ident: ref_4 article-title: Privacy attitudes and privacy behaviour: A review of current research on the privacy paradox phenomenon publication-title: Comput. Secur. doi: 10.1016/j.cose.2015.07.002 – ident: ref_77 doi: 10.3115/v1/D14-1179 – ident: ref_53 doi: 10.1109/CVPR.2016.90 – volume: 39 start-page: 1137 year: 2016 ident: ref_60 article-title: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2577031 – reference: 41305309 - Sensors (Basel). 2025 Nov 14;25(22):6957. doi: 10.3390/s25226957.
SSID	ssj0023338
Score	2.460723
Snippet	The increasing use of AI systems for face, object, action, scene, and emotion recognition raises significant privacy risks, particularly when processing...
SourceID	doaj proquest gale pubmed crossref
SourceType	Open Website Aggregation Database Index Database
StartPage	6105
SubjectTerms	Algorithms Artificial Intelligence Biometrics Biometry Compliance Computer Security Data integrity data intelligibility Decision making Facial recognition technology hard biometrics Humans Machine learning Multimedia multimodal data Ontology Privacy privacy engineering Privacy, Right of re-identification Semantics soft biometrics Usability User behavior
SummonAdditionalLinks	– databaseName: Health & Medical Collection dbid: 7X7 link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB5B4QAHypvQggxC4kLUTeLE9qnaAiu4lKqiYm-R7dglB5KSTYv4NfxVZhzvlofEhVOixLYszXg8nz3zDcCLUhbOm1ylhZUIUCrjU1W6LNVVmVveCC8cD8UmxOGhXC7VUTxwW8WwyrVNDIa66S2dke-hm0ExhLj97J99TalqFN2uxhIaV-Ealc0mPRfLS8BVIP6a2IQKhPZ7K8rSxFHK3_agQNX_t0H-w80M281i-38nehtuRUeTzSfNuANXXHcXbv5CP3gPfszZCWpgGk54W8sCUxUC4fk3PTi2WIdtMfRr2TE6lCnli7APaGS-xCAg1nsWUnhDAgp7o0fNjob2Qtvv-AwMENjqFdNdw2LiU-h2TK56ePvUjp_bLg7SNzTj9yzSqN-Hk8Xbj6_fpbFgQ2rRDxhTxTOhhW5mnq5nG6uUcUr4StlZ5XQlOHelU1pWJvelQpPvhPGZl9zPpPBKFg9gq-s79wiYRoUxRe5zLdBn8tageDMlXaUcYhpdJfB8LcL6bOLlqBHPkJzrjZwTOCDhbhoQlXb40A-ndVyZdaa9b4zkpkBo6NDoyspag7jOou9UuCyBl6QaNS34cdBWx7wFnCdRZ9VzxIS4baBxTGB3rRF1tASr-lIdEni2-Y1ioosZ3bn-fGpDRP-SJ_Bw0rrNnDn25iqXj_89-A7cyKkyMYU2FLuwNQ7n7glctxdjuxqehmXxE_AVGG4 priority: 102 providerName: ProQuest
Title	A User-Centric Context-Aware Framework for Real-Time Optimisation of Multimedia Data Privacy Protection, and Information Retention Within Multimodal AI Systems
URI	https://www.ncbi.nlm.nih.gov/pubmed/41094928 https://www.proquest.com/docview/3261090061 https://www.proquest.com/docview/3261794684 https://doaj.org/article/1affdb84b3114e08886ccb606c8223e1
Volume	25
WOSCitedRecordID	wos001593938200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: DOA dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: M~E dateStart: 20010101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: 7X7 dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: BENPR dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: PIMPY dateStart: 20010101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nj9MwEB3BwgEOiG8CS2UQEheibRInto9daMUetkQVK8rJsh1bmwMpSrOLuPBX-KuMHbda4MCFS1q5TuR0xuP3kplngFclL6zTuUgLw5GgVNqlorRZqqoyN7RhjlkaNptgyyVfr0V9ZasvnxM2ygOPf9xRppxrNKe6QORucU7wyhiNsNvg0lbYQHymTOzIVKRaBTKvUUeoQFJ_tPX1mQgUyt9WnyDS_3co_gNghoVmcRfuRIRIZuPI7sE1292H21d0Ax_Azxk5Q9dJw6PZ1pAgMYUMdvZN9ZYsdvlWBAEpWSESTH2hB_mA0eFLzN4hG0dC7W2oHCHv1KBI3beXynzHzyDdgL3eENU1JFYshdNWHmOHb5_a4bzt4kU2jR_xCYn65w_hbDH_-PZ9GndaSA0u4EMqaMYUU83U-feqjRFCW8FcJcy0sqpilNrSCsUrnbtSYKy2TLvMceqmnDnBi0dw0G06-wSIQkvrIne5Ygh2nNEZUjLBbSUskhFVJfByZwH5dRTUkEhEvJnk3kwJHHvb7Dt4DezQgJ4ho2fIf3lGAq-9ZaWfqUOvjIoFBzhOr3klZ0jmMN5jVEvgcGd8GafwViKu9UmriHcSeLH_Gc3k36iozm4uxj5eoZ_TBB6PTrMfM8Wzqcj50_9xL8_gVu43HvaZC8UhHAz9hX0ON83l0G77CVxnaxaOfAI3jufLejUJ8wGPpz_m2FafnNaffwFMARDv
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3LbtQwFL0qBQlY8H4EChgEYkPUydP2AqGBMuqoZaiqVp1dcBwbsiApmbRVv4Y_4Bu510mmPCR2XbCa0YxjWcnxuffE9wHwPBGRsXko_UgLFChpbn2ZmMBXaRLquOCWm9g1m-CzmZjP5c4K_BhyYSiscuBER9RFrekd-Tq6GRRDiObnzeE3n7pG0enq0EKjg8WWOT1BybZ4Pd3A5_siDCfv995t-n1XAV-jsWp9GQdccVWMLJ0hFlrK3EhuU6lHqVEpj2OTGKlEmoc2kchLhuc2sCK2I8GtFBHOewEuIo9zEnt8fibwItR7XfWiKJKj9QVlheKqk99snmsN8LcB-MOtdeZtcv1_uzE34FrvSLNxh_ybsGKqW3D1l_KKt-H7mO3jDvPdG-xSM1eJC4X--EQ1hk2GsDSGfjvbRYfZp3wY9hFJ9Gsf5MRqy1yKskuwYRuqVWynKY-VPsVPV-ECR71iqipYn9jlLtslKeK-HZTtl7LqJ6kLWvGU9WXi78D-udyhu7Ba1ZW5D0zhhsij0IaKo09odR6gcpXCpNKgZlOpB88GyGSHXd2RDPUa4Spb4sqDtwSm5QAqFe5-qJvPWc88WaCsLXIR5xFKX4NGRaRa56hbNfqGkQk8eElQzIjQ2kZp1edl4DqpNFg2Rs2LZhHJ34O1AYFZz3SL7Ax-Hjxd_o2PiQ6eVGXqo24MNTIQsQf3OpQv1xzj1bEMxYN_T_4ELm_ufdjOtqezrYdwJaQuzBTGEa3BatscmUdwSR-35aJ57LYkg0_nDfWf88Z22A
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLUJw4P0IFDAIxIVoN4mT2AeEFpYVq8Kyqqgop-A4NuRAUrJpS38N_4Nfx9hxwkvi1gOnRIljOcnnmfnseQA8iFmkdB5yP5IMCUqSa5_HKvBFEoeSFqlOFbXFJtLlku3t8dUGfO9jYYxbZS8TraAuamnWyMdoZhgfQlQ_Y-3cIlaz-dP9L76pIGV2WvtyGh1EttXxEdK39ZPFDP_1wzCcv3j7_KXvKgz4EhVX63MapCIVxUSb_cRCcp4rnuqEy0miRJJSqmLFBUvyUMccZZRKcx1oRvWEpZqzCPs9BZtoktNwBJurxevV-4HuRcj-ulxGUcQn47WJEcV3iH_TgLZQwN_q4A8j1yq7-YX_-TNdhPPOxCbTbk5cgg1VXYZzvyRevALfpmQX555v17ZLSWyOrq-tPz0SjSLz3mGNoEVPdtCU9k2kDHmD4vWzc38itSY2eNmG3pCZaAVZNeWhkMd4tLkvsNVjIqqCuJAv-9iOISn27F3Zfior10ldmBEviEsgfxV2T-QLXYNRVVfqBhCBUyWPQh2KFK1FLfMAOS1nKuEK2ZxIPLjfwyfb7zKSZMjkDMayAWMePDPAGhqYJOL2Qt18zJxMygKhdZEzmkdIihWqG5ZImSOjlWg1Rirw4JGBZWZEXdsIKVzEBo7TJA3LpsiGUWGiWvBgq0dj5mTgOvsJRQ_uDbfxN5ktKVGp-qBrY0ocMOrB9Q7xw5gpPk15yG7-u_O7cAYRnr1aLLdvwdnQlGc2_h3RFoza5kDdhtPysC3XzR03Pwl8OGms_wAahoEn
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%3Ajournal&rft.genre=article&rft.atitle=A+User-Centric+Context-Aware+Framework+for+Real-Time+Optimisation+of+Multimedia+Data+Privacy+Protection%2C+and+Information+Retention+Within+Multimodal+AI+Systems&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Topalli%2C+Ndricim&rft.au=Badii%2C+Atta&rft.date=2025-10-03&rft.issn=1424-8220&rft.eissn=1424-8220&rft.volume=25&rft.issue=19&rft_id=info:doi/10.3390%2Fs25196105&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon