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.

Chapter Contents:

• 12.1 Introduction
• 12.2 Hash functions
• 12.3 PhotoDNA
• 12.4 Content-based image classification
• 12.4.1 Feature-descriptor-based image classification
• 12.4.2 CNN-based image classification
• 12.5 Encryption-based image classification
• 12.6 Experiments
• 12.6.1 Experimental framework
• 12.6.2 PhotoDNA hash values dataset
• 12.7 Results
• 12.8 Discussion
• 12.9 Conclusion
• References

Inspec keywords: Big Data; learning (artificial intelligence); security of data; reverse engineering; data privacy

Other keywords: big data service providers; Indecent Images; machine-learning-based classification attacks; PhotoDNA hash; big data companies; privacy protection capability; privacy verification; IIOC; machine learning; perceptual fuzzy hash technology; Microsoft

Subjects: Data security; Knowledge engineering techniques; Data handling techniques