REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection

TL;DR

REVEAL introduces a reasoning-enhanced framework and benchmark for forensic analysis of AI-generated images, emphasizing explainability, verifiable evidence chains, and improved cross-domain detection.

Contribution

The paper presents REVEAL, a novel benchmark and forensic framework that leverages explicit evidence chains and reinforcement learning for explainable AI-generated image detection.

Findings

Significantly improved cross-domain generalization.

More faithful explanations compared to baseline detectors.

Effective evidence-based reasoning enhances detection accuracy.

Abstract

The rapid progress of visual generative models has made AI-generated images increasingly difficult to distinguish from authentic ones, posing growing risks to social trust and information integrity. This motivates detectors that are not only accurate but also forensically explainable. While recent multimodal approaches improve interpretability, many rely on post-hoc rationalizations or coarse visual cues, without constructing verifiable chains of evidence, thus often leading to poor generalization. We introduce REVEAL-Bench, a reasoning-enhanced multimodal benchmark for AI-generated image forensics, structured around explicit chains of forensic evidence derived from lightweight expert models and consolidated into step-by-step chain-of-evidence traces. Based on this benchmark, we propose REVEAL (\underline{R}easoning-\underline{e}nhanced Forensic E\underline{v}id\underline{e}nce \underline{A}na\underline{l}ysis), an explainable forensic framework trained with expert-grounded reinforcement learning. Our reward design jointly promotes detection accuracy, evidence-grounded reasoning stability, and explanation faithfulness. Extensive experiments demonstrate significantly improved cross-domain generalization and more faithful explanations to baseline detectors. All data and codes will be released.