Empirical evaluation of PRNU fingerprint variation for mismatched imaging pipelines

Show simple item record

dc.contributor.author Joshi, Sharad
dc.contributor.author Korus, Pawel
dc.contributor.author Khanna, Nitin
dc.contributor.author Memon, Nasir
dc.date.accessioned 2020-04-20T07:26:30Z
dc.date.available 2020-04-20T07:26:30Z
dc.date.issued 2020-04
dc.identifier.citation Joshi, Sharad; Korus, Pawel; Khanna, Nitin and Memon, Nasir, "Empirical evaluation of PRNU fingerprint variation for mismatched imaging pipelines", arXiv, Cornell University Library, DOI: arXiv:2004.01929, Apr. 2020. en_US
dc.identifier.uri http://arxiv.org/abs/2004.01929
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/5329
dc.description.abstract We assess the variability of PRNU-based camera fingerprints with mismatched imaging pipelines (e.g., different camera ISP or digital darkroom software). We show that camera fingerprints exhibit non-negligible variations in this setup, which may lead to unexpected degradation of detection statistics in real-world use-cases. We tested 13 different pipelines, including standard digital darkroom software and recent neural-networks. We observed that correlation between fingerprints from mismatched pipelines drops on average to 0.38 and the PCE detection statistic drops by over 40%. The degradation in error rates is the strongest for small patches commonly used in photo manipulation detection, and when neural networks are used for photo development. At a fixed 0.5% FPR setting, the TPR drops by 17 ppt (percentage points) for 128 px and 256 px patches.
dc.description.statementofresponsibility by Sharad Joshi, Pawel Korus, Nitin Khanna and Nasir Memon
dc.language.iso en_US en_US
dc.publisher Cornell University Library en_US
dc.title Empirical evaluation of PRNU fingerprint variation for mismatched imaging pipelines en_US
dc.type Pre-Print en_US
dc.relation.journal arXiv

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


My Account