Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917017463816192 |
|---|---|
| author | Wen, Siwei Ye, Junyan Feng, Peilin Kang, Hengrui Wen, Zichen Chen, Yize Wu, Jiang Wu, Wenjun He, Conghui Li, Weijia |
| author_facet | Wen, Siwei Ye, Junyan Feng, Peilin Kang, Hengrui Wen, Zichen Chen, Yize Wu, Jiang Wu, Wenjun He, Conghui Li, Weijia |
| contents | With the rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, synthetic images have become increasingly prevalent in everyday life, posing new challenges for authenticity assessment and detection. Despite the effectiveness of existing methods in evaluating image authenticity and locating forgeries, these approaches often lack human interpretability and do not fully address the growing complexity of synthetic data. To tackle these challenges, we introduce FakeVLM, a specialized large multimodal model designed for both general synthetic image and DeepFake detection tasks. FakeVLM not only excels in distinguishing real from fake images but also provides clear, natural language explanations for image artifacts, enhancing interpretability. Additionally, we present FakeClue, a comprehensive dataset containing over 100,000 images across seven categories, annotated with fine-grained artifact clues in natural language. FakeVLM demonstrates performance comparable to expert models while eliminating the need for additional classifiers, making it a robust solution for synthetic data detection. Extensive evaluations across multiple datasets confirm the superiority of FakeVLM in both authenticity classification and artifact explanation tasks, setting a new benchmark for synthetic image detection. The code, model weights, and dataset can be found here: https://github.com/opendatalab/FakeVLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14905 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation Wen, Siwei Ye, Junyan Feng, Peilin Kang, Hengrui Wen, Zichen Chen, Yize Wu, Jiang Wu, Wenjun He, Conghui Li, Weijia Computer Vision and Pattern Recognition With the rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, synthetic images have become increasingly prevalent in everyday life, posing new challenges for authenticity assessment and detection. Despite the effectiveness of existing methods in evaluating image authenticity and locating forgeries, these approaches often lack human interpretability and do not fully address the growing complexity of synthetic data. To tackle these challenges, we introduce FakeVLM, a specialized large multimodal model designed for both general synthetic image and DeepFake detection tasks. FakeVLM not only excels in distinguishing real from fake images but also provides clear, natural language explanations for image artifacts, enhancing interpretability. Additionally, we present FakeClue, a comprehensive dataset containing over 100,000 images across seven categories, annotated with fine-grained artifact clues in natural language. FakeVLM demonstrates performance comparable to expert models while eliminating the need for additional classifiers, making it a robust solution for synthetic data detection. Extensive evaluations across multiple datasets confirm the superiority of FakeVLM in both authenticity classification and artifact explanation tasks, setting a new benchmark for synthetic image detection. The code, model weights, and dataset can be found here: https://github.com/opendatalab/FakeVLM. |
| title | Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.14905 |