From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918430326652928 |
|---|---|
| author | Liang, Mengfei Qu, Yiting Jiang, Yukun Backes, Michael Zhang, Yang |
| author_facet | Liang, Mengfei Qu, Yiting Jiang, Yukun Backes, Michael Zhang, Yang |
| contents | The rapid evolution of AI-generated images poses growing challenges to information integrity and media authenticity. Existing detection approaches face limitations in robustness, interpretability, and generalization across diverse generative models, particularly when relying on a single source of visual evidence. We introduce AIFo (Agent-based Image Forensics), a training-free framework that formulates AI-generated image detection as a multi-stage forensic analysis process through multi-agent collaboration. The framework integrates a set of forensic tools, including reverse image search, metadata extraction, pre-trained classifiers, and vision-language model analysis, and resolves insufficient or conflicting evidence through a structured multi-agent debate mechanism. An optional memory-augmented module further enables the framework to incorporate information from historical cases. We evaluate AIFo on a benchmark of 6,000 images spanning controlled laboratory settings and challenging real-world scenarios, where it achieves 97.05% accuracy and consistently outperforms traditional classifiers and strong vision-language model baselines. These findings demonstrate the effectiveness of agent-based procedural reasoning for AI-generated image detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00181 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection Liang, Mengfei Qu, Yiting Jiang, Yukun Backes, Michael Zhang, Yang Computer Vision and Pattern Recognition Cryptography and Security The rapid evolution of AI-generated images poses growing challenges to information integrity and media authenticity. Existing detection approaches face limitations in robustness, interpretability, and generalization across diverse generative models, particularly when relying on a single source of visual evidence. We introduce AIFo (Agent-based Image Forensics), a training-free framework that formulates AI-generated image detection as a multi-stage forensic analysis process through multi-agent collaboration. The framework integrates a set of forensic tools, including reverse image search, metadata extraction, pre-trained classifiers, and vision-language model analysis, and resolves insufficient or conflicting evidence through a structured multi-agent debate mechanism. An optional memory-augmented module further enables the framework to incorporate information from historical cases. We evaluate AIFo on a benchmark of 6,000 images spanning controlled laboratory settings and challenging real-world scenarios, where it achieves 97.05% accuracy and consistently outperforms traditional classifiers and strong vision-language model baselines. These findings demonstrate the effectiveness of agent-based procedural reasoning for AI-generated image detection. |
| title | From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection |
| topic | Computer Vision and Pattern Recognition Cryptography and Security |
| url | https://arxiv.org/abs/2511.00181 |