Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection

TL;DR

This paper introduces REFORM, a reasoning-based framework for multimodal manipulation detection that emphasizes explicit forensic reasoning to improve generalization to unseen manipulation types.

Contribution

The paper proposes a novel three-stage curriculum and a large-scale dataset with reasoning annotations to enhance generalizable manipulation detection.

Findings

REFORM achieves state-of-the-art accuracy on multiple benchmarks.

The approach significantly improves generalization to unseen manipulation patterns.

Extensive experiments validate the effectiveness of explicit forensic reasoning.

Abstract

Recent advances in generative AI have significantly enhanced the realism of multimodal media manipulation, thereby posing substantial challenges to manipulation detection. Existing manipulation detection and grounding approaches predominantly focus on manipulation type classification under result-oriented supervision, which not only lacks interpretability but also tends to overfit superficial artifacts. In this paper, we argue that generalizable detection requires incorporating explicit forensic reasoning, rather than merely classifying a limited set of manipulation types, which fails to generalize to unseen manipulation patterns. To this end, we propose REFORM, a reasoning-driven framework that shifts learning from outcome fitting to process modeling. REFORM adopts a three-stage curriculum that first induces forensic rationales, then aligns reasoning with final judgments, and finally refines logical consistency via reinforcement learning. To support this paradigm, we introduce ROM, a large-scale dataset with rich reasoning annotations. Extensive experiments show that REFORM establishes new state-of-the-art performance with superior generalization, achieving 81.52% ACC on ROM, 76.65% ACC on DGM4, and 74.9 F1 on MMFakeBench.