Unsupervised JPEG Domain Adaptation for Practical Digital Image Forensics

Rony Abecidan (1) , Vincent Itier (1, 2) , Jérémie Boulanger (1) , Patrick Bas (1)

1 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
2 IMT Nord Europe - Ecole nationale supérieure Mines-Télécom Lille Douai

Domain adaptation is a major issue for doing practical forensics. Since examined images are likely to come from a different development pipeline compared to the ones used for training our models, that may disturb them by a lot, degrading their performances. In this paper, we present a method enabling to make a forgery detector more robust to distributions different but related to its training one, inspired by [1]. The strategy exhibited in this paper foster a detector to find a feature invariant space where source and target distributions are close. Our study deals more precisely with discrepancies observed due to JPEG compressions and our experiments reveal that the proposed adaptation scheme can reasonably reduce the mismatch, even with a rather small target set with no labels when the source domain is properly selected. On top of that, when a small portion of labelled target images is available this method reduces the gap with mix training while being unsupervised.

Domaines: Traitement du signal et de l'image [eess.SP]

Rony Abecidan, Vincent Itier, Jérémie Boulanger, Patrick Bas. Unsupervised JPEG Domain Adaptation for Practical Digital Image Forensics. IEEE International Workshop on Information Forensics and Security (WIFS 2021), Dec 2021, Montpellier, France. ⟨hal-03374780v2⟩