Mirage: Unveiling Hidden Artifacts in Synthetic Images with Large Vision-Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914075424849920 |
|---|---|
| author | Sharma, Pranav Garg, Shivank Toshniwal, Durga |
| author_facet | Sharma, Pranav Garg, Shivank Toshniwal, Durga |
| contents | Recent advances in image generation models have led to models that produce synthetic images that are increasingly difficult for standard AI detectors to identify, even though they often remain distinguishable by humans. To identify this discrepancy, we introduce \textbf{Mirage}, a curated dataset comprising a diverse range of AI-generated images exhibiting visible artifacts, where current state-of-the-art detection methods largely fail. Furthermore, we investigate whether Large Vision-Language Models (LVLMs), which are increasingly employed as substitutes for human judgment in various tasks, can be leveraged for explainable AI image detection. Our experiments on both Mirage and existing benchmark datasets demonstrate that while LVLMs are highly effective at detecting AI-generated images with visible artifacts, their performance declines when confronted with images lacking such cues. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03840 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mirage: Unveiling Hidden Artifacts in Synthetic Images with Large Vision-Language Models Sharma, Pranav Garg, Shivank Toshniwal, Durga Computer Vision and Pattern Recognition Recent advances in image generation models have led to models that produce synthetic images that are increasingly difficult for standard AI detectors to identify, even though they often remain distinguishable by humans. To identify this discrepancy, we introduce \textbf{Mirage}, a curated dataset comprising a diverse range of AI-generated images exhibiting visible artifacts, where current state-of-the-art detection methods largely fail. Furthermore, we investigate whether Large Vision-Language Models (LVLMs), which are increasingly employed as substitutes for human judgment in various tasks, can be leveraged for explainable AI image detection. Our experiments on both Mirage and existing benchmark datasets demonstrate that while LVLMs are highly effective at detecting AI-generated images with visible artifacts, their performance declines when confronted with images lacking such cues. |
| title | Mirage: Unveiling Hidden Artifacts in Synthetic Images with Large Vision-Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.03840 |