Diffusion Model Attribution via Spectral Coupling of Denoiser Responses

2026-06-26

AI Summary

Existing methods struggle to reliably trace generated images back to their source diffusion models, particularly when model architectures or autoencoders are similar. This work proposes a non-intrusive fingerprinting approach that leverages, for the first time, the energy redistribution characteristics of the denoising score function in the spatial frequency domain to construct an intrinsic model signature—requiring no registration, inversion, or optimization. By applying frequency-controllable perturbation probes, the method extracts spectral geometric features from denoising responses using only standard forward passes, yielding Spectral Denoising Signatures (SDS). Evaluated across eight diffusion models, the approach achieves 99.9% source attribution accuracy and maintains robust performance under cross-domain prompt transfer, attaining 96.2% accuracy—significantly outperforming current non-intrusive alternatives.

Abstract

Attributing a generated image to its source diffusion model is a fundamental challenge in provenance verification and intellectual property protection. This problem is particularly difficult because diffusion models trained on different datasets can converge to similar score functions and thus similar output distributions, making the generated images themselves unreliable as attribution evidence. Existing non-invasive methods either fail on architecturally similar variants or rely on signals that vanish when models share the same autoencoder. We propose Spectral Denoising Signatures (SDS), a non-invasive attribution method that identifies the source model by fingerprinting each candidate model's denoising behavior. Our key insight is that a model's denoising score function exhibits a distinctive spectral geometry, reflected in how it redistributes energy across spatial frequency bands during denoising. By probing this behavior with frequency-controlled perturbations, SDS extracts a stable signature that is intrinsic to the model, requiring only standard forward passes with no inversion, optimization, or generation-time enrollment. Our results demonstrate that SDS achieves approximately 99.9% accuracy across eight diverse diffusion models and 96.2% under cross-domain prompt shift, outperforming non-invasive baselines across variations in training data, architecture, and training procedure, establishing spectral geometry as a principled and practical basis for diffusion model attribution. Code is available at: https://github.com/Pragati-Meshram/SGS

Problem

• diffusion model attribution
• provenance verification
• spectral geometry
• denoising behavior
• intellectual property protection

Innovation

• Spectral Geometry
• Denoising Signature
• Diffusion Model Attribution
• Non-invasive Fingerprinting
• Frequency-domain Analysis