8 citations · 15 across the 7 of their papers we have counts for
8 papers
DinoLizer: Separating VAE and Diffusion Artifacts in Generative Inpainting Localization
Minh Thong Doi, Vincent Itier, Jan Butora +2
We introduce DinoLizer, a DINOv2-based localizer of manipulated areas in generative inpainting. The model is trained to focus on semantically altered regions by treating reconstruc…
Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix
Etienne Levecque, Aurélien Noirault, Tomáš Pevn{ý} +3
Steganographic schemes dedicated to generated images modify the seed vector in the latent space to embed a message. Whereas most steganalysis methods attempt to detect the embeddin…
Dual JPEG Compatibility: a Reliable and Explainable Tool for Image Forensics
Etienne Levecque, Jan Butora, Patrick Bas
Given a JPEG pipeline (compression or decompression), this paper demonstrates how to find the antecedent of an 8x8 block. If it exists, the block is considered compatible with the…
Finding Incompatible Blocks for Reliable JPEG Steganalysis
Etienne Levecque, Jan Butora, Patrick Bas
This article presents a refined notion of incompatible JPEG images for a quality factor of 100. It can be used to detect the presence of steganographic schemes embedding in DCT coe…
The Adobe Hidden Feature and its Impact on Sensor Attribution
Jan Butora, Patrick Bas
If the extraction of sensor fingerprints represents nowadays an important forensic tool for sensor attribution, it has been shown recently that images coming from several sensors w…
Compatibility and Timing Attacks for JPEG Steganalysis
Etienne Levecque, Patrick Bas, Jan Butora
This paper introduces a novel compatibility attack to detect a steganographic message embedded in the DCT domain of a JPEG image at high-quality factors (close to 100). Because the…
Side-Informed Steganography for JPEG Images by Modeling Decompressed Images
Jan Butora, Patrick Bas
Side-informed steganography has always been among the most secure approaches in the field. However, a majority of existing methods for JPEG images use the side information, here th…
Errorless Robust JPEG Steganography using Outputs of JPEG Coders
Jan Butora, Pauline Puteaux, Patrick Bas
Robust steganography is a technique of hiding secret messages in images so that the message can be recovered after additional image processing. One of the most popular processing o…