Lossless Copyright Protection via Intrinsic Model Fingerprinting

2026-01-29

AI Summary

This work addresses the vulnerability of diffusion models to unauthorized replication, a challenge inadequately mitigated by existing copyright protection methods that often degrade model performance or fail in black-box API settings. To overcome these limitations, the authors propose TrajPrint, a novel framework that enables fully lossless, training-free, and model-agnostic copyright verification. TrajPrint extracts an intrinsic manifold fingerprint from the model by deterministically tracing its generation trajectories, and leverages a dual-anchor strategy combined with statistical hypothesis testing to achieve robust copyright attribution under black-box conditions. The method demonstrates strong resilience against common model modifications, including fine-tuning and pruning, thereby offering a practical and reliable solution for intellectual property protection in deployed diffusion models.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Data transparency and provenance
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The exceptional performance of diffusion models establishes them as high-value intellectual property but exposes them to unauthorized replication. Existing protection methods either modify the model to embed watermarks, which impairs performance, or extract model fingerprints by manipulating the denoising process, rendering them incompatible with black-box APIs. In this paper, we propose TrajPrint, a completely lossless and training-free framework that verifies model copyright by extracting unique manifold fingerprints formed during deterministic generation. Specifically, we first utilize a watermarked image as an anchor and exactly trace the path back to its trajectory origin, effectively locking the model fingerprint mapped by this path. Subsequently, we implement a joint optimization strategy that employs dual-end anchoring to synthesize a specific fingerprint noise, which strictly adheres to the target manifold for robust watermark recovery. As input, it enables the protected target model to recover the watermarked image, while failing on non-target models. Finally, we achieved verification via atomic inference and statistical hypothesis testing. Extensive experiments demonstrate that TrajPrint achieves lossless verification in black-box API scenarios with superior robustness against model modifications.

Problem

• lossless copyright protection
• diffusion models
• model fingerprinting
• black-box API
• intellectual property

Innovation

• model fingerprinting
• lossless watermarking
• diffusion models
• black-box verification
• manifold trajectory