DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization

TL;DR

DiffusionPrint introduces a contrastive learning framework that captures robust generative fingerprints for diffusion-based inpainting localization, significantly enhancing forgery detection accuracy across various models.

Contribution

It presents a novel patch-level contrastive learning method that learns forensic signals resilient to spectral distortions in diffusion-based inpainting.

Findings

Improves localization accuracy by up to +28% on unseen mask types.

Generalizes well to unseen generative architectures.

Enhances existing fusion-based IFL frameworks with discriminative forensic features.

Abstract

Modern diffusion-based inpainting models pose significant challenges for image forgery localization (IFL), as their full regeneration pipelines reconstruct the entire image via a latent decoder, disrupting the camera-level noise patterns that existing forensic methods rely on. We propose DiffusionPrint, a patch-level contrastive learning framework that learns a forensic signal robust to the spectral distortions introduced by latent decoding. It exploits the fact that inpainted regions generated by the same model share a consistent generative fingerprint, using this as a self-supervisory signal. DiffusionPrint trains a convolutional backbone via a MoCo-style objective with cross-category hard negative mining and a generator-aware classification head, producing a forensic feature map that serves as a highly discriminative secondary modality in fusion-based IFL frameworks. Integrated into TruFor, MMFusion, and a lightweight fusion baseline, DiffusionPrint consistently improves localization across multiple generative models, with gains of up to +28% on mask types unseen during fine-tuning and confirmed generalization to unseen generative architectures. Code is available at https://github.com/mever-team/diffusionprint