Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.09688 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913022148083712 |
|---|---|
| author | Zhang, Jianwei Cao, Sihan Zhang, Chaoning Hong, Ziming Huang, Jiaxin Zheng, Pengcheng Qin, Caiyan Dong, Wei Yang, Yang Liu, Tongliang |
| author_facet | Zhang, Jianwei Cao, Sihan Zhang, Chaoning Hong, Ziming Huang, Jiaxin Zheng, Pengcheng Qin, Caiyan Dong, Wei Yang, Yang Liu, Tongliang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09688 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps Zhang, Jianwei Cao, Sihan Zhang, Chaoning Hong, Ziming Huang, Jiaxin Zheng, Pengcheng Qin, Caiyan Dong, Wei Yang, Yang Liu, Tongliang Computer Vision and Pattern Recognition 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. |
| title | Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.09688 |