Reliable Camera Model Identification Through Uncertainty Estimation

Pan J, Maier A, Lorch B, Rieß C (2021)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2021

URI: https://faui1-files.cs.fau.de/public/publications/mmsec/2021-Pan-IWBF.pdf

DOI: 10.1109/IWBF50991.2021.9465097

Abstract

Camera model identification is a standard task in digital image forensics. Learning-based approaches achieve state-of-the-art performance, but they are sensitive to so-called out-of-distribution (OOD) data due to a mismatch between the training and testing distribution. This may result in a significant reduction in classifier performance that is, unfortunately, not easy to anticipate for a forensic analyst.
In this work, we investigate possibilities for adding reliability measures to the task of camera model identification. We leverage learning architectures that include an uncertainty measure with every prediction that can be reported back to an analyst. To this end, we investigate deep ensembles and Bayesian neural networks (BNNs). We compare both methods against a standard CNN with softmax statistics as uncertainty metric. We demonstrate in several experiments that both probabilistic approaches provide simultaneously state-of-the-art classification performance and
reliable uncertainty estimates on OOD data. The uncertainty of deep ensembles is more accurate on OOD camera models, while BNN uncertainties are more accurate on OOD post-processing.

Authors with CRIS profile

Related research project(s)

How to cite

APA:

Pan, J., Maier, A., Lorch, B., & Rieß, C. (2021). Reliable Camera Model Identification Through Uncertainty Estimation. In Proceedings of the IEEE International Workshop on Biometrics and Forensics.

MLA:

Pan, Jiarong, et al. "Reliable Camera Model Identification Through Uncertainty Estimation." Proceedings of the IEEE International Workshop on Biometrics and Forensics 2021.

BibTeX: Download