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

2025-10-31

AI Summary

The proliferation of AI-generated images severely undermines media credibility, while existing detection methods suffer from poor interpretability, limited adaptability, and coarse-grained reasoning. To address these challenges, this paper proposes the first multi-agent collaborative framework for interpretable AI-image detection, explicitly modeling human forensic investigation workflows. The framework integrates reverse image search, metadata analysis, multimodal classification, and synergistic reasoning between vision-language models (VLMs) and large language models (LLMs), forming a dynamic decision system equipped with debate mechanisms and memory augmentation. Its key innovations include cross-source evidence integration, robust discrimination under conflicting evidence, and continual learning capability for emerging generative models. Evaluated on a benchmark of 6,000 images, the framework achieves 97.05% accuracy—significantly outperforming single-model classifiers and state-of-the-art VLM-based approaches.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The rapid evolution of AI-generated images poses unprecedented challenges to information integrity and media authenticity. Existing detection approaches suffer from fundamental limitations: traditional classifiers lack interpretability and fail to generalize across evolving generative models, while vision-language models (VLMs), despite their promise, remain constrained to single-shot analysis and pixel-level reasoning. To address these challenges, we introduce AIFo (Agent-based Image Forensics), a novel training-free framework that emulates human forensic investigation through multi-agent collaboration. Unlike conventional methods, our framework employs a set of forensic tools, including reverse image search, metadata extraction, pre-trained classifiers, and VLM analysis, coordinated by specialized LLM-based agents that collect, synthesize, and reason over cross-source evidence. When evidence is conflicting or insufficient, a structured multi-agent debate mechanism allows agents to exchange arguments and reach a reliable conclusion. Furthermore, we enhance the framework with a memory-augmented reasoning module that learns from historical cases to improve future detection accuracy. Our comprehensive evaluation spans 6,000 images across both controlled laboratory settings and challenging real-world scenarios, including images from modern generative platforms and diverse online sources. AIFo achieves 97.05% accuracy, substantially outperforming traditional classifiers and state-of-the-art VLMs. These results demonstrate that agent-based procedural reasoning offers a new paradigm for more robust, interpretable, and adaptable AI-generated image detection.

Problem

• Detecting AI-generated images with robust interpretability across evolving models
• Overcoming limitations of single-shot analysis in existing detection methods
• Resolving conflicting evidence through multi-agent forensic investigation collaboration

Innovation

• Multi-agent collaboration for forensic image analysis
• Structured debate mechanism resolves conflicting evidence
• Memory-augmented reasoning learns from historical cases