Privacy verification of photoDNA based on machine learning
Book chapter
Authors | Nadeem, Muhammad Shahroz, Franqueira, Virginia N. L. and Zhai, Xiaojun |
---|---|
Abstract | PhotoDNA 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. |
Keywords | Privacy; PhotoDNA; Machine Learning; Security |
Year | 2019 |
Publisher | The Institution of Engineering and Technology (IET) |
ISBN | 9781785617478 |
Web address (URL) | http://hdl.handle.net/10545/624203 |
hdl:10545/624203 | |
File | File Access Level Open |
Publication dates | 09 Oct 2019 |
Publication process dates | |
Deposited | 08 Oct 2019, 07:55 |
Accepted | Mar 2019 |
Contributors | University of Derby, College of Engineering and Technology and University of Essex, School of Computer Science and Electronic Engineering |
https://repository.derby.ac.uk/item/93y41/privacy-verification-of-photodna-based-on-machine-learning
Download files
225
total views0
total downloads2
views this month0
downloads this month