Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Yanzhu, Liu, Xiao, Wang, Yuexuan, Soumik, Mondal
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.20461
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915848291090432
author Liu, Yanzhu
Liu, Xiao
Wang, Yuexuan
Soumik, Mondal
author_facet Liu, Yanzhu
Liu, Xiao
Wang, Yuexuan
Soumik, Mondal
contents With the rapid proliferation of powerful image generators, accurate detection of AI-generated images has become essential for maintaining a trustworthy online environment. However, existing deepfake detectors often generalize poorly to images produced by unseen generators. Notably, despite being trained under vastly different paradigms, such as diffusion or autoregressive modeling, many modern image generators share common final architectural components that serve as the last stage for converting intermediate representations into images. Motivated by this insight, we propose to "contaminate" real images using the generator's final component and train a detector to distinguish them from the original real images. We further introduce a taxonomy based on generators' final components and categorize 21 widely used generators accordingly, enabling a comprehensive investigation of our method's generalization capability. Using only 100 samples from each of three representative categories, our detector-fine-tuned on the DINOv3 backbone-achieves an average accuracy of 98.83% across 22 testing sets from unseen generators.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20461
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Exploiting the Final Component of Generator Architectures for AI-Generated Image Detection
Liu, Yanzhu
Liu, Xiao
Wang, Yuexuan
Soumik, Mondal
Computer Vision and Pattern Recognition
With the rapid proliferation of powerful image generators, accurate detection of AI-generated images has become essential for maintaining a trustworthy online environment. However, existing deepfake detectors often generalize poorly to images produced by unseen generators. Notably, despite being trained under vastly different paradigms, such as diffusion or autoregressive modeling, many modern image generators share common final architectural components that serve as the last stage for converting intermediate representations into images. Motivated by this insight, we propose to "contaminate" real images using the generator's final component and train a detector to distinguish them from the original real images. We further introduce a taxonomy based on generators' final components and categorize 21 widely used generators accordingly, enabling a comprehensive investigation of our method's generalization capability. Using only 100 samples from each of three representative categories, our detector-fine-tuned on the DINOv3 backbone-achieves an average accuracy of 98.83% across 22 testing sets from unseen generators.
title Exploiting the Final Component of Generator Architectures for AI-Generated Image Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.20461