MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning
This addresses a critical safety issue in healthcare by providing interpretable detection of medical deepfakes, though it is incremental as it builds on existing detection and reasoning approaches.
The paper tackles the problem of detecting manipulated medical scans, such as lesion implantation or removal, which threatens clinical trust, by introducing MedForge, a method that achieves state-of-the-art detection accuracy with trustworthy, expert-aligned explanations.
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.