Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2603.12796v1
• Date: Fri, 13 Mar 2026 08:56:49 GMT
• Title: Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting
• Abstract summary: 3D Gaussian Splatting (3DGS) deliver high-quality rendering, yet the Gaussian representation exposes a new attack surface.<n>This attack poisons training images, excessively inducing Gaussian growth to cause resource exhaustion.<n>We propose textbfSpectral Defense in Gaussian and image fields.
• Score: 63.29941651174379
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in 3D Gaussian Splatting (3DGS) deliver high-quality rendering, yet the Gaussian representation exposes a new attack surface, the resource-targeting attack. This attack poisons training images, excessively inducing Gaussian growth to cause resource exhaustion. Although efficiency-oriented methods such as smoothing, thresholding, and pruning have been explored, these spatial-domain strategies operate on visible structures but overlook how stealthy perturbations distort the underlying spectral behaviors of training data. As a result, poisoned inputs introduce abnormal high-frequency amplifications that mislead 3DGS into interpreting noisy patterns as detailed structures, ultimately causing unstable Gaussian overgrowth and degraded scene fidelity. To address this, we propose \textbf{Spectral Defense} in Gaussian and image fields. We first design a 3D frequency filter to selectively prune Gaussians exhibiting abnormally high frequencies. Since natural scenes also contain legitimate high-frequency structures, directly suppressing high frequencies is insufficient, and we further develop a 2D spectral regularization on renderings, distinguishing naturally isotropic frequencies while penalizing anisotropic angular energy to constrain noisy patterns. Experiments show that our defense builds robust, accurate, and secure 3DGS, suppressing overgrowth by up to $5.92\times$, reducing memory by up to $3.66\times$, and improving speed by up to $4.34\times$ under attacks.

Related papers

• KC-3DGS: Kurtosis-Constrained Gaussian Splatting for High-Fidelity View Synthesis [28.10448224660243]
  3D Gaussian Splatting (3DGS) enables real-time novel view synthesis by representing scenes as collections of anisotropic Gaussians optimized via differentiableization.<n>Standard pixel-space losses (L1, SSIM) constrain only aggregate reconstruction error, permitting the optimization to redistribute error across frequency scales.<n>We propose KC-3DGS, which augments 3DGS training with wavelet-domain supervision based on natural image statistics.
  arXiv  Detail & Related papers  (2026-06-02T04:04:24Z)
• Augmented Radiance Field: A General Framework for Enhanced Gaussian Splatting [16.088036048557914]
  3D Gaussian Splatting (3DGS) has emerged as the leading method for radiance field reconstruction.<n>We propose a novel enhanced Gaussian kernel that explicitly models specular effects through view-dependent opacity.<n>Our method not only surpasses state-of-the-art NeRF methods in rendering performance but also achieves greater parameter efficiency.
  arXiv  Detail & Related papers  (2026-02-23T14:55:31Z)
• DefenseSplat: Enhancing the Robustness of 3D Gaussian Splatting via Frequency-Aware Filtering [16.115612700186023]
  3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images.<n>Recent studies reveal its vulnerability to adversarial corruptions in input views, where imperceptible yet consistent perturbations can drastically degrade rendering quality.<n>We propose a frequency-aware defense strategy that reconstructs training views by filtering high-frequency noise while preserving low-frequency content.
  arXiv  Detail & Related papers  (2026-02-22T20:00:02Z)
• PrismGS: Physically-Grounded Anti-Aliasing for High-Fidelity Large-Scale 3D Gaussian Splatting [23.277915756682944]
  3D Gaussian Splatting (3DGS) has recently enabled real-time rendering in compact scenes, but scaling to large urban environments introduces severe aliasing artifacts.<n>We propose PrismGS, a physically-grounded regularization framework that improves the intrinsic rendering behavior of 3D Gaussians.
  arXiv  Detail & Related papers  (2025-10-09T06:21:45Z)
• 3D Gaussian Splat Vulnerabilities [20.065766098524698]
  We introduce view-dependent Gaussian appearances to embed adversarial content visible only from specific viewpoints.<n>We demonstrate DAGGER, a targeted adversarial attack directly perturbing 3D Gaussians without access to underlying training data.<n>These attacks highlight underexplored vulnerabilities in 3DGS, introducing a new potential threat to robotic learning for autonomous navigation and other safety-critical 3DGS applications.
  arXiv  Detail & Related papers  (2025-05-30T22:21:22Z)
• Mipmap-GS: Let Gaussians Deform with Scale-specific Mipmap for Anti-aliasing Rendering [81.88246351984908]
  We propose a unified optimization method to make Gaussians adaptive for arbitrary scales. Inspired by the mipmap technique, we design pseudo ground-truth for the target scale and propose a scale-consistency guidance loss to inject scale information into 3D Gaussians. Our method outperforms 3DGS in PSNR by an average of 9.25 dB for zoom-in and 10.40 dB for zoom-out.
  arXiv  Detail & Related papers  (2024-08-12T16:49:22Z)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)
• Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting [55.71424195454963]
  Spec-Gaussian is an approach that utilizes an anisotropic spherical Gaussian appearance field instead of spherical harmonics. Our experimental results demonstrate that our method surpasses existing approaches in terms of rendering quality. This improvement extends the applicability of 3D GS to handle intricate scenarios with specular and anisotropic surfaces.
  arXiv  Detail & Related papers  (2024-02-24T17:22:15Z)
• GES: Generalized Exponential Splatting for Efficient Radiance Field Rendering [112.16239342037714]
  GES (Generalized Exponential Splatting) is a novel representation that employs Generalized Exponential Function (GEF) to model 3D scenes. With the aid of a frequency-modulated loss, GES achieves competitive performance in novel-view synthesis benchmarks.
  arXiv  Detail & Related papers  (2024-02-15T17:32:50Z)
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS [55.85673901231235]
  We introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework.
  arXiv  Detail & Related papers  (2023-11-28T21:39:20Z)

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.