用CNN和CLIP模型检测并识别AI生成图像来源，效果优于主流方法。
Team NYCU at Defactify4: Robust Detection and Source Identification of AI-Generated Images Using CNN and CLIP-Based Models
- 融合RGB、频域特征与重建误差，用EfficientNet-B0做检测。
- CLIP-ViT在图像扰动下表现更鲁棒，准确率超基线模型。
- 在Defactify 4竞赛中排名前三，适合内容真实性验证场景。
随着生成式AI的快速发展，AI生成图像日益逼真，引发对创意归属、虚假信息和内容真实性的担忧。本文针对AI生成图像的检测与源模型识别问题，采用基于CNN和CLIP-ViT的分类器。CNN方法以EfficientNet-B0为骨干网络，输入包括RGB通道、频率特征和重建误差；CLIP-ViT则使用预训练的CLIP图像编码器提取特征，并结合SVM进行分类。在Defactify 4数据集上的评估显示，该方法在两项任务中均表现优异，其中CLIP-ViT对图像扰动具有更强鲁棒性。相比AEROBLADE和OCC-CLIP等基线方法，本方案达到竞争性结果。值得注意的是，本方法在Defactify 4竞赛中位列总体前三，体现了其有效性与泛化能力。所有代码已开源：https://github.com/uuugaga/Defactify_4。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。