Frequency-Domain Analysis of Traces for the Detection of AI-based Compression

Bergmann S, Moussa D, Brand F, Kaup A, Rieß C (2023)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2023

Conference Proceedings Title: 2023 International Workshop on Biometrics and Forensics (IWBF)

Event location: Barcelona ES

URI: https://faui1-files.cs.fau.de/public/publications/mmsec/2023-Bergmann-IWBF.pdf

DOI: 10.1109/iwbf57495.2023.10157489

Open Access Link: https://faui1-files.cs.fau.de/public/publications/mmsec/2023-Bergmann-IWBF.pdf

Abstract

The JPEG algorithm is the most popular compression method on the internet. Its properties have been extensively studied in image forensics for examining image origin and authenticity. However, the JPEG standard will in the near future be extended with AI-based compression. This approach is fundamentally different from the classic JPEG algorithm, and requires an entirely new set of forensics tools.
As a first step towards forensic tools for AI compression, we present a first investigation of forensic traces in HiFiC, the current state-of-the-art AI-based compression method. We investigate the frequency space of the compressed images, and identify two types of traces, which likely arise from GAN upsampling and in homogeneous areas. We evaluate the detectability on different patch sizes and unseen postprocessing, and report a detectability of 96.37%. Our empirical results also suggest that further, yet unidentified, compression traces can be expected in the spatial domain.

Authors with CRIS profile

Sandra Bergmann Lehrstuhl für Informatik 1 (IT-Sicherheitsinfrastrukturen) Denise Moussa Lehrstuhl für Informatik 1 (IT-Sicherheitsinfrastrukturen) Fabian Brand Lehrstuhl für Multimediakommunikation und Signalverarbeitung Andre Kaup Lehrstuhl für Multimediakommunikation und Signalverarbeitung Christian Rieß Lehrstuhl für Informatik 1 (IT-Sicherheitsinfrastrukturen)

How to cite

APA:

Bergmann, S., Moussa, D., Brand, F., Kaup, A., & Rieß, C. (2023). Frequency-Domain Analysis of Traces for the Detection of AI-based Compression. In IEEE (Eds.), 2023 International Workshop on Biometrics and Forensics (IWBF). Barcelona, ES.

MLA:

Bergmann, Sandra, et al. "Frequency-Domain Analysis of Traces for the Detection of AI-based Compression." Proceedings of the International Workshop on Biometrics and Forensics 2023, Barcelona Ed. IEEE, 2023.

BibTeX: Download