Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cai, Hongfei, Liu, Chi, Shen, Sheng, Qu, Youyang, Gui, Peng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.02879
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908299875581952
author Cai, Hongfei
Liu, Chi
Shen, Sheng
Qu, Youyang
Gui, Peng
author_facet Cai, Hongfei
Liu, Chi
Shen, Sheng
Qu, Youyang
Gui, Peng
contents The rapid progression of generative AI (GenAI) technologies has heightened concerns regarding the misuse of AI-generated imagery. To address this issue, robust detection methods have emerged as particularly compelling, especially in challenging conditions where the targeted GenAI models are out-of-distribution or the generated images have been subjected to perturbations during transmission. This paper introduces a multi-feature fusion framework designed to enhance spatial forensic feature representations with incorporating three complementary components, namely noise correlation analysis, image gradient information, and pretrained vision encoder knowledge, using a cross-source attention mechanism. Furthermore, to identify spectral abnormality in synthetic images, we propose a frequency-aware architecture that employs the Frequency-Adaptive Dilated Convolution, enabling the joint modeling of spatial and spectral features while maintaining low computational complexity. Our framework exhibits exceptional generalization performance across fourteen diverse GenAI systems, including text-to-image diffusion models, autoregressive approaches, and post-processed deepfake methods. Notably, it achieves significantly higher mean accuracy in cross-model detection tasks when compared to existing state-of-the-art techniques. Additionally, the proposed method demonstrates resilience against various types of real-world image noise perturbations such as compression and blurring. Extensive ablation studies further corroborate the synergistic benefits of fusing multi-model forensic features with frequency-aware learning, underscoring the efficacy of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02879
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust AI-Synthesized Image Detection via Multi-feature Frequency-aware Learning
Cai, Hongfei
Liu, Chi
Shen, Sheng
Qu, Youyang
Gui, Peng
Graphics
The rapid progression of generative AI (GenAI) technologies has heightened concerns regarding the misuse of AI-generated imagery. To address this issue, robust detection methods have emerged as particularly compelling, especially in challenging conditions where the targeted GenAI models are out-of-distribution or the generated images have been subjected to perturbations during transmission. This paper introduces a multi-feature fusion framework designed to enhance spatial forensic feature representations with incorporating three complementary components, namely noise correlation analysis, image gradient information, and pretrained vision encoder knowledge, using a cross-source attention mechanism. Furthermore, to identify spectral abnormality in synthetic images, we propose a frequency-aware architecture that employs the Frequency-Adaptive Dilated Convolution, enabling the joint modeling of spatial and spectral features while maintaining low computational complexity. Our framework exhibits exceptional generalization performance across fourteen diverse GenAI systems, including text-to-image diffusion models, autoregressive approaches, and post-processed deepfake methods. Notably, it achieves significantly higher mean accuracy in cross-model detection tasks when compared to existing state-of-the-art techniques. Additionally, the proposed method demonstrates resilience against various types of real-world image noise perturbations such as compression and blurring. Extensive ablation studies further corroborate the synergistic benefits of fusing multi-model forensic features with frequency-aware learning, underscoring the efficacy of our approach.
title Robust AI-Synthesized Image Detection via Multi-feature Frequency-aware Learning
topic Graphics
url https://arxiv.org/abs/2504.02879