Machine/Deep Learning Techniques for Multimedia Security

dc.authorwosidHeidari, Arash/AAK-9761-2021
dc.contributor.authorHeidari, Arash
dc.contributor.authorNavimipour, Nima Jafari
dc.contributor.authorAzad, Poupak
dc.date.accessioned2024-10-15T19:39:19Z
dc.date.available2024-10-15T19:39:19Z
dc.date.issued2023
dc.departmentKadir Has Universityen_US
dc.department-temp[Heidari, Arash] Halic Univ, Dept Software Engn, Istanbul, Turkey; [Navimipour, Nima Jafari] Kadir Has Univ, Dept Comp Engn, Istanbul, Turkey; [Azad, Poupak] Univ Manitoba, Dept Comp Sci, Winnipeg, MB, Canadaen_US
dc.description.abstractMultimedia security based on Machine Learning (ML)/ Deep Learning (DL) is a field of study that focuses on using ML/DL techniques to protect multimedia data such as images, videos, and audio from unauthorized access, manipulation, or theft. Developing and implementing algorithms and systems that use ML/DL techniques to detect and prevent security breaches in multimedia data is the main subject of this field. These systems use techniques like watermarking, encryption, and digital signature verification to protect multimedia data. The advantages of using ML/DL in multimedia security include improved accuracy, scalability, and automation. ML/DL algorithms can improve the accuracy of detecting security threats and help identify multimedia data vulnerabilities. Additionally, ML models can be scaled up to handle large amounts of multimedia data, making them helpful in protecting big datasets. Finally, ML/DL algorithms can automate the process of multimedia security, making it easier and more efficient to protect multimedia data. The disadvantages of using ML/DL in multimedia security include data availability, complexity, and black box models. ML and DL algorithms require large amounts of data to train the models, which can sometimes be challenging. Developing and implementing ML algorithms can also be complex, requiring specialized skills and knowledge. Finally, ML/DL models are often black box models, which means it can be difficult to understand how they make their decisions. This can be a challenge when explaining the decisions to stakeholders or auditors. Overall, multimedia security based on ML/DL is a promising area of research with many potential benefits. However, it also presents challenges that must be addressed to ensure the security and privacy of multimedia data.en_US
dc.description.woscitationindexBook Citation Index – Science
dc.identifier.citation0
dc.identifier.doi[WOS-DOI-BELIRLENECEK-2]
dc.identifier.endpage68en_US
dc.identifier.isbn9781839536946
dc.identifier.isbn9781839536939
dc.identifier.scopusqualityN/A
dc.identifier.startpage51en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12469/6304
dc.identifier.volume61en_US
dc.identifier.wosWOS:001262241600004
dc.identifier.wosqualityN/A
dc.institutionauthorOzbek, Muge
dc.institutionauthorÖzbek, Müge
dc.language.isoenen_US
dc.publisherinst Engineering Tech-ieten_US
dc.relation.ispartofseriesIET COMPUTING SERIES
dc.relation.publicationcategoryKitap Bölümü - Uluslararasıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subject[No Keyword Available]en_US
dc.titleMachine/Deep Learning Techniques for Multimedia Securityen_US
dc.typeBook Parten_US
dspace.entity.typePublication
relation.isAuthorOfPublicationdf2eb7f6-e48a-48b8-a5f1-3ed07a133b44
relation.isAuthorOfPublication.latestForDiscoverydf2eb7f6-e48a-48b8-a5f1-3ed07a133b44

Files