Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines

Sharad Joshi; Pawel Korus; Nitin Khanna; Nasir Memon

doi:10.1109/WIFS49906.2020.9360911

Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines

Sharad Joshi, Pawel Korus, Nitin Khanna, Nasir Memon

Center for Cyber Security

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English (US)
Title of host publication	2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728199306
DOIs	https://doi.org/10.1109/WIFS49906.2020.9360911
State	Published - Dec 6 2020
Event	2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020 - New York, United States Duration: Dec 6 2020 → Dec 11 2020

Publication series

Name	2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020

Conference

Conference	2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020
Country/Territory	United States
City	New York
Period	12/6/20 → 12/11/20

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing
Information Systems and Management
Safety, Risk, Reliability and Quality

Access to Document

10.1109/WIFS49906.2020.9360911

Cite this

Joshi, S., Korus, P., Khanna, N., & Memon, N. (2020). Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines. In 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020 Article 9360911 (2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WIFS49906.2020.9360911

Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines. / Joshi, Sharad; Korus, Pawel; Khanna, Nitin et al.
2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9360911 (2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Joshi, S, Korus, P, Khanna, N & Memon, N 2020, Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines. in 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020., 9360911, 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020, New York, United States, 12/6/20. https://doi.org/10.1109/WIFS49906.2020.9360911

Joshi S, Korus P, Khanna N, Memon N. Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines. In 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9360911. (2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020). doi: 10.1109/WIFS49906.2020.9360911

@inproceedings{2f1c0ca5ea9348feaf01a115df7c4d90,

title = "Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines",

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.",

author = "Sharad Joshi and Pawel Korus and Nitin Khanna and Nasir Memon",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020 ; Conference date: 06-12-2020 Through 11-12-2020",

year = "2020",

month = dec,

day = "6",

doi = "10.1109/WIFS49906.2020.9360911",

language = "English (US)",

series = "2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020",

}

TY - GEN

T1 - Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines

AU - Joshi, Sharad

AU - Korus, Pawel

AU - Khanna, Nitin

AU - Memon, Nasir

PY - 2020/12/6

Y1 - 2020/12/6

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85102515122&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85102515122&partnerID=8YFLogxK

U2 - 10.1109/WIFS49906.2020.9360911

DO - 10.1109/WIFS49906.2020.9360911

M3 - Conference contribution

AN - SCOPUS:85102515122

T3 - 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020

BT - 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Workshop on Information Forensics and Security, WIFS 2020

Y2 - 6 December 2020 through 11 December 2020

ER -

Empirical Evaluation of PRNU Fingerprint Variation for Mismatched Imaging Pipelines

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this