DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Keita, Mamadou, Hamidouche, Wassim, Eutamene, Hessen Bougueffa, Taleb-Ahmed, Abdelmalik, Hadid, Abdenour
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916710255165440
author Keita, Mamadou
Hamidouche, Wassim
Eutamene, Hessen Bougueffa
Taleb-Ahmed, Abdelmalik
Hadid, Abdenour
author_facet Keita, Mamadou
Hamidouche, Wassim
Eutamene, Hessen Bougueffa
Taleb-Ahmed, Abdelmalik
Hadid, Abdenour
contents This paper introduces DeeCLIP, a novel framework for detecting AI-generated images using CLIP-ViT and fusion learning. Despite significant advancements in generative models capable of creating highly photorealistic images, existing detection methods often struggle to generalize across different models and are highly sensitive to minor perturbations. To address these challenges, DeeCLIP incorporates DeeFuser, a fusion module that combines high-level and low-level features, improving robustness against degradations such as compression and blurring. Additionally, we apply triplet loss to refine the embedding space, enhancing the model's ability to distinguish between real and synthetic content. To further enable lightweight adaptation while preserving pre-trained knowledge, we adopt parameter-efficient fine-tuning using low-rank adaptation (LoRA) within the CLIP-ViT backbone. This approach supports effective zero-shot learning without sacrificing generalization. Trained exclusively on 4-class ProGAN data, DeeCLIP achieves an average accuracy of 89.00% on 19 test subsets composed of generative adversarial network (GAN) and diffusion models. Despite having fewer trainable parameters, DeeCLIP outperforms existing methods, demonstrating superior robustness against various generative models and real-world distortions. The code is publicly available at https://github.com/Mamadou-Keita/DeeCLIP for research purposes.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images
Keita, Mamadou
Hamidouche, Wassim
Eutamene, Hessen Bougueffa
Taleb-Ahmed, Abdelmalik
Hadid, Abdenour
Computer Vision and Pattern Recognition
Cryptography and Security
This paper introduces DeeCLIP, a novel framework for detecting AI-generated images using CLIP-ViT and fusion learning. Despite significant advancements in generative models capable of creating highly photorealistic images, existing detection methods often struggle to generalize across different models and are highly sensitive to minor perturbations. To address these challenges, DeeCLIP incorporates DeeFuser, a fusion module that combines high-level and low-level features, improving robustness against degradations such as compression and blurring. Additionally, we apply triplet loss to refine the embedding space, enhancing the model's ability to distinguish between real and synthetic content. To further enable lightweight adaptation while preserving pre-trained knowledge, we adopt parameter-efficient fine-tuning using low-rank adaptation (LoRA) within the CLIP-ViT backbone. This approach supports effective zero-shot learning without sacrificing generalization. Trained exclusively on 4-class ProGAN data, DeeCLIP achieves an average accuracy of 89.00% on 19 test subsets composed of generative adversarial network (GAN) and diffusion models. Despite having fewer trainable parameters, DeeCLIP outperforms existing methods, demonstrating superior robustness against various generative models and real-world distortions. The code is publicly available at https://github.com/Mamadou-Keita/DeeCLIP for research purposes.
title DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images
topic Computer Vision and Pattern Recognition
Cryptography and Security
url https://arxiv.org/abs/2504.19876