ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Models

TL;DR

ForenX leverages multimodal large language models with specialized prompts and a new dataset to improve AI-generated image detection and provide human-like explanations, enhancing both accuracy and interpretability.

Contribution

The paper introduces ForenX, a novel approach that combines MLLMs with forensic prompts and a dedicated dataset to improve detection and explanation of AI-generated images.

Findings

Enhanced forgery detection accuracy on benchmarks.

Improved explanation quality verified by subjective evaluations.

Limited manual annotations significantly boost performance.

Abstract

Advances in generative models have led to AI-generated images visually indistinguishable from authentic ones. Despite numerous studies on detecting AI-generated images with classifiers, a gap persists between such methods and human cognitive forensic analysis. We present ForenX, a novel method that not only identifies the authenticity of images but also provides explanations that resonate with human thoughts. ForenX employs the powerful multimodal large language models (MLLMs) to analyze and interpret forensic cues. Furthermore, we overcome the limitations of standard MLLMs in detecting forgeries by incorporating a specialized forensic prompt that directs the MLLMs attention to forgery-indicative attributes. This approach not only enhance the generalization of forgery detection but also empowers the MLLMs to provide explanations that are accurate, relevant, and comprehensive. Additionally, we introduce ForgReason, a dataset dedicated to descriptions of forgery evidences in AI-generated images. Curated through collaboration between an LLM-based agent and a team of human annotators, this process provides refined data that further enhances our model's performance. We demonstrate that even limited manual annotations significantly improve explanation quality. We evaluate the effectiveness of ForenX on two major benchmarks. The model's explainability is verified by comprehensive subjective evaluations.