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

2026-03-13

AI Summary

This work addresses the vulnerability of 3D Gaussian Splatting (3DGS) to resource-oriented attacks, which induce uncontrolled Gaussian proliferation and excessive resource consumption. To counter this, we introduce spectral analysis into 3DGS security for the first time, proposing a defense mechanism that jointly applies 3D Gaussian frequency filtering and 2D rendering spectral regularization. This approach effectively discriminates and suppresses anomalous high-frequency components introduced by poisoned images while preserving natural geometric details. By integrating anisotropic angular energy penalties with Gaussian pruning, our method significantly reduces computational overhead without compromising scene fidelity. Experiments demonstrate that under attack, our solution reduces the number of Gaussians by 5.92×, decreases memory usage by 3.66×, and accelerates rendering by 4.34×, achieving both robust security and high efficiency.

Technology Category

• Computer Vision: 3D Computer Vision
• Natural Language Processing: Safety and Robustness
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• 3D Gaussian Splatting
• resource-targeting attack
• spectral defense
• Gaussian overgrowth
• high-frequency amplification

Innovation

• Spectral Defense
• 3D Gaussian Splatting
• resource-targeting attack
• frequency filtering
• spectral regularization