Intermediate Representations are Strong AI-Generated Image Detectors
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915983581511680 |
|---|---|
| author | Huang, Zhenhan Chen, Pin-Yu Pedapati, Tejaswini Gao, Jianxi |
| author_facet | Huang, Zhenhan Chen, Pin-Yu Pedapati, Tejaswini Gao, Jianxi |
| contents | The rapid advancement in generative AI models has enabled the creation of photorealistic images. At the same time, there are growing concerns about the potential misuse and dangers of generated content, as well as a pressing need for effective AI-generated image detectors. However, current training-based detection techniques are typically computationally costly and can hardly be generalized to unseen data domains, while training-free methods fall short in detection performance. To bridge this gap, we propose a search-based method employing data embedding sensitivity in intermediate layers to detect AI-generated images. Given a set of real and AI-generated images, our method examines the similarity between original image embeddings and perturbed image embeddings, and detects AI-generated images based on the similarity. We examine the proposed method on two comprehensive benchmarks: GenImage and Forensics Small. Our method exhibits improved performance across different datasets compared to both training-free and training-based state-of-the-art methods. On average, our method achieves the largest performance gain on the Forensics Small benchmark by 39.61% compared to the best training-free method and 5.14% compared to the best training-based method in AUROC score. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04358 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Intermediate Representations are Strong AI-Generated Image Detectors Huang, Zhenhan Chen, Pin-Yu Pedapati, Tejaswini Gao, Jianxi Computer Vision and Pattern Recognition Machine Learning The rapid advancement in generative AI models has enabled the creation of photorealistic images. At the same time, there are growing concerns about the potential misuse and dangers of generated content, as well as a pressing need for effective AI-generated image detectors. However, current training-based detection techniques are typically computationally costly and can hardly be generalized to unseen data domains, while training-free methods fall short in detection performance. To bridge this gap, we propose a search-based method employing data embedding sensitivity in intermediate layers to detect AI-generated images. Given a set of real and AI-generated images, our method examines the similarity between original image embeddings and perturbed image embeddings, and detects AI-generated images based on the similarity. We examine the proposed method on two comprehensive benchmarks: GenImage and Forensics Small. Our method exhibits improved performance across different datasets compared to both training-free and training-based state-of-the-art methods. On average, our method achieves the largest performance gain on the Forensics Small benchmark by 39.61% compared to the best training-free method and 5.14% compared to the best training-based method in AUROC score. |
| title | Intermediate Representations are Strong AI-Generated Image Detectors |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2605.04358 |