AI Paper Atlas

Research map / 3D vision / Gaussian splatting

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

ICML 2026 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
initialize AdLift from 3DGS fitted on 2D adversarial perturbations (AdLift*) instead of from the raw asset (ablation)AdLift-VU · IP2P editing, novel views (4 scenes avg)CLIPs: 0.8181 -> 0.8087Improved
use untargeted VAE loss instead of targeted VAE loss (ablation)AdLift* · IP2P editing, novel views (4 scenes avg)CLIPs: 0.8296 -> 0.8087 CLIPs; 0.1758 -> 0.1802 CLIPdMixed
use L-PGD lifted perturbations rather than directly fitting 3DGS on per-view 2D protected images (ablation)AdLift-VU · IP2P editing, training views (4 scenes avg)CLIPs: 0.8368 -> 0.8139Improved
use L-PGD lifted perturbations rather than directly fitting 3DGS on per-view 2D protected images (ablation)AdLift-VU · IP2P editing, novel views (4 scenes avg)CLIPs: 0.8488 -> 0.8181Improved
use strict rendering-space bound (AdLift) instead of soft-constraint GaussianMarker at similar PSNRFace scene protection · Face, novel views, matched PSNRCLIPs: 0.8578 -> 0.7786Improved
perturb all Gaussian features (GuardSplat-Full) instead of SH features only (ablation)GuardSplat · Face, novel views, matched PSNRCLIPs: 0.8666 -> 0.8535 CLIPs at lower PSNR 25.7744 -> 23.7877No clear effect
apply AdLift*-VU protection trained on IP2P to unseen MagicBrush editingAdLift*-VU · Face, MagicBrush, novel viewsCLIPs: 0.8635 -> 0.7659Improved
apply AdLift*-VT protection to unseen SDEdit editingAdLift*-VT · Face, SDEdit, novel viewsCLIPd: 0.1708 -> 0.1751No clear effect
apply AdLift*-VU protection to unseen DGE 3D editingAdLift*-VU · Face, DGE, novel viewsCLIPd: 0.1218 -> 0.1200No clear effect
apply AdLift*-VU protection to unseen Instruct-GS2GS editingAdLift*-VU · Face, Instruct-GS2GS, novel viewsCLIPd: 0.1108 -> 0.0857Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy