Team NYCU at Defactify4: Robust Detection and Source Identification of AI-Generated Images Using CNN and CLIP-Based Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Tsan-Tsung, Chen, I-Wei, Chen, Kuan-Ting, Chiang, Shang-Hsuan, Peng, Wen-Chih
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917956694310912
author Yang, Tsan-Tsung
Chen, I-Wei
Chen, Kuan-Ting
Chiang, Shang-Hsuan
Peng, Wen-Chih
author_facet Yang, Tsan-Tsung
Chen, I-Wei
Chen, Kuan-Ting
Chiang, Shang-Hsuan
Peng, Wen-Chih
contents With the rapid advancement of generative AI, AI-generated images have become increasingly realistic, raising concerns about creativity, misinformation, and content authenticity. Detecting such images and identifying their source models has become a critical challenge in ensuring the integrity of digital media. This paper tackles the detection of AI-generated images and identifying their source models using CNN and CLIP-ViT classifiers. For the CNN-based classifier, we leverage EfficientNet-B0 as the backbone and feed with RGB channels, frequency features, and reconstruction errors, while for CLIP-ViT, we adopt a pretrained CLIP image encoder to extract image features and SVM to perform classification. Evaluated on the Defactify 4 dataset, our methods demonstrate strong performance in both tasks, with CLIP-ViT showing superior robustness to image perturbations. Compared to baselines like AEROBLADE and OCC-CLIP, our approach achieves competitive results. Notably, our method ranked Top-3 overall in the Defactify 4 competition, highlighting its effectiveness and generalizability. All of our implementations can be found in https://github.com/uuugaga/Defactify_4
format Preprint
id arxiv_https___arxiv_org_abs_2503_10718
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Team NYCU at Defactify4: Robust Detection and Source Identification of AI-Generated Images Using CNN and CLIP-Based Models
Yang, Tsan-Tsung
Chen, I-Wei
Chen, Kuan-Ting
Chiang, Shang-Hsuan
Peng, Wen-Chih
Computer Vision and Pattern Recognition
Artificial Intelligence
With the rapid advancement of generative AI, AI-generated images have become increasingly realistic, raising concerns about creativity, misinformation, and content authenticity. Detecting such images and identifying their source models has become a critical challenge in ensuring the integrity of digital media. This paper tackles the detection of AI-generated images and identifying their source models using CNN and CLIP-ViT classifiers. For the CNN-based classifier, we leverage EfficientNet-B0 as the backbone and feed with RGB channels, frequency features, and reconstruction errors, while for CLIP-ViT, we adopt a pretrained CLIP image encoder to extract image features and SVM to perform classification. Evaluated on the Defactify 4 dataset, our methods demonstrate strong performance in both tasks, with CLIP-ViT showing superior robustness to image perturbations. Compared to baselines like AEROBLADE and OCC-CLIP, our approach achieves competitive results. Notably, our method ranked Top-3 overall in the Defactify 4 competition, highlighting its effectiveness and generalizability. All of our implementations can be found in https://github.com/uuugaga/Defactify_4
title Team NYCU at Defactify4: Robust Detection and Source Identification of AI-Generated Images Using CNN and CLIP-Based Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.10718