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

2026-04-06

AI Summary

This work addresses the growing risk of intellectual property leakage in 3D Gaussian generative models due to unauthorized fine-tuning of publicly released pre-trained weights. To counter this threat, we propose GaussLock, the first anti-fine-tuning defense framework specifically designed for 3D Gaussian models. GaussLock embeds structured perturbations into the parameter space through authorized knowledge distillation and an attribute-aware trap loss that targets key geometric and appearance attributes—including position, scale, rotation, opacity, and color. This approach preserves performance on legitimate fine-tuning tasks while significantly degrading the geometric coherence and visual fidelity of unauthorized reconstructions. Extensive experiments demonstrate that GaussLock effectively increases LPIPS and reduces PSNR on large-scale models, thereby providing active immunity against illicit model adaptation.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Data transparency and provenance

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.

Problem

• 3D generative models
• unauthorized fine-tuning
• intellectual property protection
• Gaussian representations
• model security

Innovation

• 3D generative models
• fine-tuning defense
• attribute-space traps
• Gaussian splatting
• model immunization