Show simple item record

dc.contributor.authorNadeem, Muhammad Shahroz
dc.contributor.authorFranqueira, Virginia N. L.
dc.contributor.authorZhai, Xiaojun
dc.date.accessioned2019-10-08T07:55:51Z
dc.date.available2019-10-08T07:55:51Z
dc.date.issued2019-10-09
dc.identifier.citationNadeem, M. S., Franqueira, V. N. L. and Zhai, X (2019). 'Privacy verification of photoDNA based on machine learning', In Ren, W., Wang, L., Choo, K. K. R. and Xhafa F. (eds.) 'Security and privacy for big data, cloud computing and applications'. Hertfordshire: The Institution of Engineering and Technology, pp. 263-280.en_US
dc.identifier.isbn9781785617478
dc.identifier.urihttp://hdl.handle.net/10545/624203
dc.description.abstractPhotoDNA is a perceptual fuzzy hash technology designed and developed by Microsoft. It is deployed by all major big data service providers to detect Indecent Images of Children (IIOC). Protecting the privacy of individuals is of paramount importance in such images. Microsoft claims that a PhotoDNA hash cannot be reverse engineered into the original image; therefore, it is not possible to identify individuals or objects depicted in the image. In this chapter, we evaluate the privacy protection capability of PhotoDNA by testing it against machine learning. Specifically, our aim is to detect the presence of any structural information that might be utilized to compromise the privacy of the individuals via classification. Due to the widespread usage of PhotoDNA as a deterrent to IIOC by big data companies, ensuring its ability to protect privacy would be crucial. In our experimentation, we achieved a classification accuracy of 57.20%.This result indicates that PhotoDNA is resistant to machine-learning-based classification attacks.en_US
dc.description.sponsorshipThe first author is a GTA, funded by the University of Derby.en_US
dc.language.isoenen_US
dc.publisherThe Institution of Engineering and Technology (IET)en_US
dc.relation.urlhttps://shop.theiet.org/security-and-privacy-for-big-data-cloud-computing-and-applicationsen_US
dc.subjectPrivacyen_US
dc.subjectPhotoDNAen_US
dc.subjectMachine Learningen_US
dc.subjectSecurityen_US
dc.titlePrivacy verification of photoDNA based on machine learningen_US
dc.typeBook chapteren_US
dc.contributor.departmentUniversity of Derby, College of Engineering and Technologyen_US
dc.contributor.departmentUniversity of Essex, School of Computer Science and Electronic Engineeringen_US
dcterms.dateAccepted2019-03
dc.author.detail783783en_US


This item appears in the following Collection(s)

Show simple item record