Detecting Localized Deepfakes: How Well Do Synthetic Image Detectors Handle Inpainting?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pandolfini, Serafino, Pellegrini, Lorenzo, Ferrara, Matteo, Maltoni, Davide
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918254986919936
author Pandolfini, Serafino
Pellegrini, Lorenzo
Ferrara, Matteo
Maltoni, Davide
author_facet Pandolfini, Serafino
Pellegrini, Lorenzo
Ferrara, Matteo
Maltoni, Davide
contents The rapid progress of generative AI has enabled highly realistic image manipulations, including inpainting and region-level editing. These approaches preserve most of the original visual context and are increasingly exploited in cybersecurity-relevant threat scenarios. While numerous detectors have been proposed for identifying fully synthetic images, their ability to generalize to localized manipulations remains insufficiently characterized. This work presents a systematic evaluation of state-of-the-art detectors, originally trained for the deepfake detection on fully synthetic images, when applied to a distinct challenge: localized inpainting detection. The study leverages multiple datasets spanning diverse generators, mask sizes, and inpainting techniques. Our experiments show that models trained on a large set of generators exhibit partial transferability to inpainting-based edits and can reliably detect medium- and large-area manipulations or regeneration-style inpainting, outperforming many existing ad hoc detection approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2512_16688
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Detecting Localized Deepfakes: How Well Do Synthetic Image Detectors Handle Inpainting?
Pandolfini, Serafino
Pellegrini, Lorenzo
Ferrara, Matteo
Maltoni, Davide
Computer Vision and Pattern Recognition
The rapid progress of generative AI has enabled highly realistic image manipulations, including inpainting and region-level editing. These approaches preserve most of the original visual context and are increasingly exploited in cybersecurity-relevant threat scenarios. While numerous detectors have been proposed for identifying fully synthetic images, their ability to generalize to localized manipulations remains insufficiently characterized. This work presents a systematic evaluation of state-of-the-art detectors, originally trained for the deepfake detection on fully synthetic images, when applied to a distinct challenge: localized inpainting detection. The study leverages multiple datasets spanning diverse generators, mask sizes, and inpainting techniques. Our experiments show that models trained on a large set of generators exhibit partial transferability to inpainting-based edits and can reliably detect medium- and large-area manipulations or regeneration-style inpainting, outperforming many existing ad hoc detection approaches.
title Detecting Localized Deepfakes: How Well Do Synthetic Image Detectors Handle Inpainting?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.16688