3 papers
cs.CV2025
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…
cs.CR2025
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…
cs.CR2024
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…