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

TL;DR

This paper introduces a spectral defense method for 3D Gaussian Splatting that detects and mitigates resource-targeting attacks by filtering high-frequency components and regularizing spectral patterns, enhancing robustness and efficiency.

Contribution

The paper proposes a novel spectral defense framework combining frequency filtering and spectral regularization to defend against resource-targeting attacks in 3D Gaussian Splatting.

Findings

Suppresses overgrowth by up to 5.92 times

Reduces memory usage by up to 3.66 times

Improves rendering speed by up to 4.34 times

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.