Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning

Zhihui Chen, Kai He, Qingyuan Lei, Bin Pu, Jian Zhang, Yuling Xu, Mengling Feng

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.

MedForge: Interpretable Medical Deepfake Detection via Forgery-aware 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.
Paper Structure (55 sections, 12 equations, 4 figures, 3 tables)

This paper contains 55 sections, 12 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Medical Deepfake Benchmarks.
  4. Interpretable Deepfake Detection.
  5. MedForge-90K Dataset
  6. Forgery Pipeline
  7. Human Expert-guided Reasoning Annotation
  8. Methodology
  9. Task Formulation
  10. Stage 1: Reasoning Cold Start
  11. Stage 2: Forgery-aware GSPO
  12. Experiments
  13. Experimental Setup
  14. Main Results
  15. Reasoning Quality
  16. ...and 40 more sections

Figures (4)

  • Figure 1: Framework comparison.Left: specialized vision detectors (e.g., CNNs) output only a binary decision, offering no clinically verifiable evidence. Right-bottom: post-hoc MLLM explainers (e.g., SIDA sida) may produce plausible-sounding but ungrounded rationales, including hallucinated visual details. Right-top:MedForge-Reasoner performs pre-hoc localized reasoning by first identifying suspicious regions (blue) and then generating medically coherent, visually verifiable rationales grounded in the image evidence.
  • Figure 2: Overview of the MedForge-90K construction pipeline. The framework proceeds in three stages: medical image collection across three modalities, forgery generation via a Writer-Editor-Diagnoser loop, and human expert-guided annotation utilizing expert guidelines to generate hierarchical diagnostic reasoning.
  • Figure 3: MedForge-Reasoner Two-stage Training. SFT for cold-starting the reasoning format, followed by Forgery-aware GSPO. The GSPO stage introduced a reward function balancing visual grounding coverage and reasoning structure compliance to ensure the model localize correct forgery region before reasoning.
  • Figure 4: Qualitative Forgery Explainnation Comparison. Baselines fail due to severe hallucinations (SIDA citing "skin texture") or missed diagnoses. While Gemini-3-Pro correctly detects the forgery using general visual clues, MedForge-Reasoner delivers superior clinically rigorous rationale, explicitly grounding the verdict in anatomical logic (e.g., "absence of mass effect") rather than generic visual analysis.