Vous êtes ici : GIPSA-lab > Formation > Thèses soutenues

Towards Digital Image Anti-Forensics via Image Restoration


Directeur de thèse :     Jean-Marc BROSSIER

Co-encadrant :     François CAYRE

École doctorale : Electronique, electrotechnique, automatique, traitement du signal (EEATS)

Spécialité : Signal, image, parole, télécoms

Structure de rattachement : Autre

Établissement d'origine : Beihang University - Chine

Financement(s) : bourse attribuée par un gouvernement étranger ; contrat à durée déterminée ; Bourse campus france ; contrat à durée déterminée


Date d'entrée en thèse : 01/09/2011

Date de soutenance : 30/04/2015


Composition du jury :
M. Jean-Marc CHASSERY, Directeur de Recherche CNRS, GIPSA-lab, Président
M. Jean-Luc DUGELAY, Professeur EURECOM, Sophia Antipolis, Rapporteur
M. Stefano TUBARO, Professeur Politecnico di Milano, Rapporteur
M. Teddy FURON, Chargé de Recherche INRIA, INRIA Rennes, Examinateur
M. Jiwu HUANG, Professeur Shenzhen University, Examinateur
M. Zhang XIONG, Professeur, Beihang University, Co-directeur
M. François CAYRE, Maître de Conférences, Grenoble INP, Co-encadrant
M. Kai WANG, Chargé de Recherche CNRS, GIPSA-lab, Co-encadrant


Résumé : Image forensics enjoys its increasing popularity as a powerful image authentication tool, working in a blind passive way without the aid of any a priori embedded information compared to fragile image watermarking. On its opponent side, image anti-forensics attacks forensic algorithms for the future development of more trustworthy forensics. When image coding or processing is involved, we notice that image anti-forensics to some extent shares a similar goal with image restoration. Both of them aim to recover the information lost during the image degradation, yet image anti-forensics has one additional indispensable forensic undetectability requirement. In this thesis, we form a new research line for image anti-forensics, by leveraging on advanced concepts/methods from image restoration meanwhile with integrations of anti-forensic strategies/terms. Under this context, this thesis contributes on the following four aspects for JPEG compression and median filtering anti-forensics: (i) JPEG anti-forensics using Total Variation based deblocking, (ii) improved Total Variation based JPEG anti-forensics with assignment problem based perceptual DCT histogram smoothing, (iii) JPEG anti-forensics using JPEG image quality enhancement based on a sophisticated image prior model and non-parametric DCT histogram smoothing based on calibration, and (iv) median filtered image quality enhancement and anti-forensics via variational deconvolution. Experimental results demonstrate the effectiveness of the proposed anti-forensic methods with a better forensic undetectability against existing forensic detectors as well as a higher visual quality of the processed image, by comparisons with the state-of-the-art methods.

GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - 33 (0)4 76 82 71 31