AdLift: Lifting Adversarial Perturbations to Safeguard 3D Gaussian Splatting Assets Against Instruction-Driven Editing

Ziming Hong, Tianyu Huang, Runnan Chen, Shanshan Ye, Mingming Gong, Bo Han, Tongliang Liu

Abstract: Recent studies have extended instruction-driven 2D editing pipelines to 3D Gaussian Splatting (3DGS), enabling faithful 3DGS asset manipulation for advanced content creation. However, it also exposes 3DGS assets to serious risks of unauthorized editing and malicious tampering. Although adversarial perturbations against editing models have proven effective for protecting 2D images, applying them to 3DGS encounters two major challenges: *view-generalizable protection* and *balancing invisibility with protection capability*. In this work, we propose AdLift, a novel editing safeguard for 3DGS that prevents instruction-driven editing across arbitrary views and dimensions by lifting strictly bounded 2D adversarial perturbations into 3D Gaussian-represented safeguard. To ensure both *protective effectiveness* and *invisibility*, these safeguard Gaussians are progressively optimized across training views using a tailored Lifted PGD, which first conducts *gradient truncation* during back-propagation from the editing model to the rendered image and applies projected gradient updates to strictly bound image-level perturbations. Then, the resulting perturbation is backpropagated to the safeguard Gaussian parameters via *image-to-Gaussian fitting*. We alternate these two steps, yielding effective and imperceptible protection that generalizes across both training and novel views. Empirically, qualitative and quantitative results demonstrate that the proposed AdLift effectively protects against state-of-the-art instruction-driven 2D and 3DGS editing.

Lay Summary: Instruction-driven 3D editing methods make it easy to modify 3D Gaussian Splatting (3DGS) assets using human instructions, but they also raise risks of unauthorized editing and malicious tampering. We propose AdLift, a safeguard that protects 3DGS assets by learning nearly invisible safeguard Gaussians. These safeguards preserve the visual appearance of the asset for users while degrading the quality of instruction-driven edits. Experiments show that AdLift provides effective and imperceptible protection against both 2D and 3DGS editing methods, with strong generalization to novel views.

Primary Area: Social Aspects

Keywords: 3D Gaussian Splatting, Instruction-driven Image/3DGS Editing, Editing Guard, Active Copyright Protection

Submission Number: 11967