MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning

TL;DR

MedForge introduces a new framework for detecting medical image forgeries that combines large-scale realistic lesion editing, expert-guided reasoning, and a localized analysis approach to improve accuracy and trustworthiness.

Contribution

The paper presents MedForge, a novel pre-hoc detection method with a large benchmark and a reasoning model that localizes suspicious regions before classifying, enhancing interpretability and reliability in medical forgery detection.

Findings

Achieves state-of-the-art detection accuracy.

Provides trustworthy, expert-aligned explanations.

Reduces hallucinations in forgery reasoning.

Abstract

Text-guided image editors can now manipulate authentic medical scans with high fidelity, enabling lesion implantation/removal that threatens clinical trust and safety. Existing defenses are inadequate for healthcare. Medical detectors are largely black-box, while MLLM-based explainers are typically post-hoc, lack medical expertise, and may hallucinate evidence on ambiguous cases. We present MedForge, a data-and-method solution for pre-hoc, evidence-grounded medical forgery detection. We introduce MedForge-90K, a large-scale benchmark of realistic lesion edits across 19 pathologies with expert-guided reasoning supervision via doctor inspection guidelines and gold edit locations. Building on it, MedForge-Reasoner performs localize-then-analyze reasoning, predicting suspicious regions before producing a verdict, and is further aligned with Forgery-aware GSPO to strengthen grounding and reduce hallucinations. Experiments demonstrate state-of-the-art detection accuracy and trustworthy, expert-aligned explanations.