Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps

TL;DR

GaussLock is a novel defense method for 3D Gaussian generative models that uses attribute-space traps to prevent unauthorized fine-tuning and protect intellectual property.

Contribution

It introduces GaussLock, the first framework to defend 3D Gaussian models against fine-tuning attacks by integrating distillation with attribute-aware traps.

Findings

GaussLock effectively neutralizes unauthorized fine-tuning attacks.

It significantly degrades the quality of unauthorized reconstructions.

It maintains high fidelity on authorized tasks.

Abstract

Recent large-scale generative models enable high-quality 3D synthesis. However, the public accessibility of pre-trained weights introduces a critical vulnerability. Adversaries can fine-tune these models to steal specialized knowledge acquired during pre-training, leading to intellectual property infringement. Unlike defenses for 2D images and language models, 3D generators require specialized protection due to their explicit Gaussian representations, which expose fundamental structural parameters directly to gradient-based optimization. We propose GaussLock, the first approach designed to defend 3D generative models against fine-tuning attacks. GaussLock is a lightweight parameter-space immunization framework that integrates authorized distillation with attribute-aware trap losses targeting position, scale, rotation, opacity, and color. Specifically, these traps systematically collapse spatial distributions, distort geometric shapes, align rotational axes, and suppress primitive visibility to fundamentally destroy structural integrity. By jointly optimizing these dual objectives, the distillation process preserves fidelity on authorized tasks while the embedded traps actively disrupt unauthorized reconstructions. Experiments on large-scale Gaussian models demonstrate that GaussLock effectively neutralizes unauthorized fine-tuning attacks. It substantially degrades the quality of unauthorized reconstructions, evidenced by significantly higher LPIPS and lower PSNR, while effectively maintaining performance on authorized fine-tuning.