EditTrack: Detecting and Attributing AI-assisted Image Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Zhengyuan, Zhang, Yuyang, Guo, Moyang, Gong, Neil Zhenqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909818888912896
author Jiang, Zhengyuan
Zhang, Yuyang
Guo, Moyang
Gong, Neil Zhenqiang
author_facet Jiang, Zhengyuan
Zhang, Yuyang
Guo, Moyang
Gong, Neil Zhenqiang
contents In this work, we formulate and study the problem of image-editing detection and attribution: given a base image and a suspicious image, detection seeks to determine whether the suspicious image was derived from the base image using an AI editing model, while attribution further identifies the specific editing model responsible. Existing methods for detecting and attributing AI-generated images are insufficient for this problem, as they focus on determining whether an image was AI-generated/edited rather than whether it was edited from a particular base image. To bridge this gap, we propose EditTrack, the first framework for this image-editing detection and attribution problem. Building on four key observations about the editing process, EditTrack introduces a novel re-editing strategy and leverages carefully designed similarity metrics to determine whether a suspicious image originates from a base image and, if so, by which model. We evaluate EditTrack on five state-of-the-art editing models across six datasets, demonstrating that it consistently achieves accurate detection and attribution, significantly outperforming five baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01173
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EditTrack: Detecting and Attributing AI-assisted Image Editing
Jiang, Zhengyuan
Zhang, Yuyang
Guo, Moyang
Gong, Neil Zhenqiang
Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
In this work, we formulate and study the problem of image-editing detection and attribution: given a base image and a suspicious image, detection seeks to determine whether the suspicious image was derived from the base image using an AI editing model, while attribution further identifies the specific editing model responsible. Existing methods for detecting and attributing AI-generated images are insufficient for this problem, as they focus on determining whether an image was AI-generated/edited rather than whether it was edited from a particular base image. To bridge this gap, we propose EditTrack, the first framework for this image-editing detection and attribution problem. Building on four key observations about the editing process, EditTrack introduces a novel re-editing strategy and leverages carefully designed similarity metrics to determine whether a suspicious image originates from a base image and, if so, by which model. We evaluate EditTrack on five state-of-the-art editing models across six datasets, demonstrating that it consistently achieves accurate detection and attribution, significantly outperforming five baselines.
title EditTrack: Detecting and Attributing AI-assisted Image Editing
topic Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2510.01173