From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liang, Mengfei, Qu, Yiting, Jiang, Yukun, Backes, Michael, Zhang, Yang
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