AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields

• URL: http://arxiv.org/abs/2510.19371v1
• Date: Wed, 22 Oct 2025 08:45:42 GMT
• Title: AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields
• Authors: Woo Jae Kim, Kyu Beom Han, Yoonki Cho, Youngju Na, Junsik Jung, Sooel Son, Sung-eui Yoon,
• Abstract summary: AegisRF aims to protect the intellectual property of 3D Neural Radiance Fields (NeRFs) from unauthorized use.<n>AegisRF learns the sensitivity to adaptively constrain geometric perturbations, preserving rendering quality while disrupting unauthorized use.
• Score: 27.06164185381677
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As Neural Radiance Fields (NeRFs) have emerged as a powerful tool for 3D scene representation and novel view synthesis, protecting their intellectual property (IP) from unauthorized use is becoming increasingly crucial. In this work, we aim to protect the IP of NeRFs by injecting adversarial perturbations that disrupt their unauthorized applications. However, perturbing the 3D geometry of NeRFs can easily deform the underlying scene structure and thus substantially degrade the rendering quality, which has led existing attempts to avoid geometric perturbations or restrict them to explicit spaces like meshes. To overcome this limitation, we introduce a learnable sensitivity to quantify the spatially varying impact of geometric perturbations on rendering quality. Building upon this, we propose AegisRF, a novel framework that consists of a Perturbation Field, which injects adversarial perturbations into the pre-rendering outputs (color and volume density) of NeRF models to fool an unauthorized downstream target model, and a Sensitivity Field, which learns the sensitivity to adaptively constrain geometric perturbations, preserving rendering quality while disrupting unauthorized use. Our experimental evaluations demonstrate the generalized applicability of AegisRF across diverse downstream tasks and modalities, including multi-view image classification and voxel-based 3D localization, while maintaining high visual fidelity. Codes are available at https://github.com/wkim97/AegisRF.

Related papers

• Taming Latent Diffusion Model for Neural Radiance Field Inpainting [63.297262813285265]
  Neural Radiance Field (NeRF) is a representation for 3D reconstruction from multi-view images. We propose tempering the diffusion model'sity with per-scene customization and mitigating the textural shift with masked training. Our framework yields state-of-the-art NeRF inpainting results on various real-world scenes.
  arXiv  Detail & Related papers  (2024-04-15T17:59:57Z)
• CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs [65.80187860906115]
  We propose a novel approach to improve NeRF's performance with sparse inputs. We first adopt a voxel-based ray sampling strategy to ensure that the sampled rays intersect with a certain voxel in 3D space. We then randomly sample additional points within the voxel and apply a Transformer to infer the properties of other points on each ray, which are then incorporated into the volume rendering.
  arXiv  Detail & Related papers  (2024-03-25T15:56:17Z)
• HarmonicNeRF: Geometry-Informed Synthetic View Augmentation for 3D Scene Reconstruction in Driving Scenarios [2.949710700293865]
  HarmonicNeRF is a novel approach for outdoor self-supervised monocular scene reconstruction. It capitalizes on the strengths of NeRF and enhances surface reconstruction accuracy by augmenting the input space with geometry-informed synthetic views. Our approach establishes new benchmarks in synthesizing novel depth views and reconstructing scenes, significantly outperforming existing methods.
  arXiv  Detail & Related papers  (2023-10-09T07:42:33Z)
• Shielding the Unseen: Privacy Protection through Poisoning NeRF with Spatial Deformation [59.302770084115814]
  We introduce an innovative method of safeguarding user privacy against the generative capabilities of Neural Radiance Fields (NeRF) models. Our novel poisoning attack method induces changes to observed views that are imperceptible to the human eye, yet potent enough to disrupt NeRF's ability to accurately reconstruct a 3D scene. We extensively test our approach on two common NeRF benchmark datasets consisting of 29 real-world scenes with high-quality images.
  arXiv  Detail & Related papers  (2023-10-04T19:35:56Z)
• GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields [12.92658687936068]
  We take advantage of generative adversarial networks (GANs) to produce realistic images and use them to enhance realism in 3D scene reconstruction with NeRFs. We learn the patch distribution of a scene using an adversarial discriminator, which provides feedback to the radiance field reconstruction. rendering artifacts are repaired directly in the underlying 3D representation by imposing multi-view path rendering constraints.
  arXiv  Detail & Related papers  (2023-06-09T17:12:35Z)
• Enhance-NeRF: Multiple Performance Evaluation for Neural Radiance Fields [2.5432277893532116]
  Neural Radiance Fields (NeRF) can generate realistic images from any viewpoint. NeRF-based models are susceptible to interference issues caused by colored "fog" noise. Our approach, coined Enhance-NeRF, adopts joint color to balance low and high reflectivity objects display.
  arXiv  Detail & Related papers  (2023-06-08T15:49:30Z)
• Clean-NeRF: Reformulating NeRF to account for View-Dependent Observations [67.54358911994967]
  This paper proposes Clean-NeRF for accurate 3D reconstruction and novel view rendering in complex scenes. Clean-NeRF can be implemented as a plug-in that can immediately benefit existing NeRF-based methods without additional input.
  arXiv  Detail & Related papers  (2023-03-26T12:24:31Z)
• DehazeNeRF: Multiple Image Haze Removal and 3D Shape Reconstruction using Neural Radiance Fields [56.30120727729177]
  We introduce DehazeNeRF as a framework that robustly operates in hazy conditions. We demonstrate successful multi-view haze removal, novel view synthesis, and 3D shape reconstruction where existing approaches fail.
  arXiv  Detail & Related papers  (2023-03-20T18:03:32Z)
• AE-NeRF: Auto-Encoding Neural Radiance Fields for 3D-Aware Object Manipulation [24.65896451569795]
  We propose a novel framework for 3D-aware object manipulation, called Auto-aware Neural Radiance Fields (AE-NeRF) Our model is formulated in an auto-encoder architecture, extracts disentangled 3D attributes such as 3D shape, appearance, and camera pose from an image. A high-quality image is rendered from the attributes through disentangled generative Neural Radiance Fields (NeRF)
  arXiv  Detail & Related papers  (2022-04-28T11:50:18Z)
• Discriminator-Free Generative Adversarial Attack [87.71852388383242]
  Agenerative-based adversarial attacks can get rid of this limitation. ASymmetric Saliency-based Auto-Encoder (SSAE) generates the perturbations. The adversarial examples generated by SSAE not only make thewidely-used models collapse, but also achieves good visual quality.
  arXiv  Detail & Related papers  (2021-07-20T01:55:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.