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

TL;DR

This paper presents AIFo, a multi-agent, training-free forensic framework that improves AI-generated image detection by combining multiple evidence sources and debate mechanisms, achieving high accuracy across diverse scenarios.

Contribution

The paper introduces AIFo, a novel agent-based forensic framework that enhances detection robustness and interpretability without training, outperforming existing methods.

Findings

Achieves 97.05% accuracy on a 6,000-image benchmark.

Outperforms traditional classifiers and vision-language baselines.

Effective in both controlled and real-world scenarios.

Abstract

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.