3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images. However, recent studies reveal its vulnerability to adversarial corruptions in input views, where imperceptible yet consistent perturbations can drastically degrade rendering quality, increase training and rendering time, and inflate memory usage, even leading to server denial-of-service. In our work, to mitigate this issue, we begin by analyzing the distinct behaviors of adversarial perturbations in the low- and high-frequency components of input images using wavelet transforms. Based on this observation, we design a simple yet effective frequency-aware defense strategy that reconstructs training views by filtering high-frequency noise while preserving low-frequency content. This approach effectively suppresses adversarial artifacts while maintaining the authenticity of the original scene. Notably, it does not significantly impair training on clean data, achieving a desirable trade-off between robustness and performance on clean inputs. Through extensive experiments under a wide range of attack intensities on multiple benchmarks, we demonstrate that our method substantially enhances the robustness of 3DGS without access to clean ground-truth supervision. By highlighting and addressing the overlooked vulnerabilities of 3D Gaussian Splatting, our work paves the way for more robust and secure 3D reconstructions.

翻译：3D高斯泼溅（3DGS）已成为从姿态图像进行实时高保真三维重建的强大范式。然而，近期研究揭示了其对输入视角中对抗性扰动的脆弱性：即使难以察觉但具有一致性的扰动也可能严重降低渲染质量、增加训练与渲染时间、扩大内存占用，甚至导致服务器拒绝服务。为缓解此问题，我们首先通过小波变换分析对抗性扰动在输入图像低频与高频分量中的不同行为特征。基于此观察，我们设计了一种简单而有效的频域感知防御策略，通过滤除高频噪声同时保留低频内容来重建训练视角。该方法能有效抑制对抗性伪影，同时保持原始场景的真实性。值得注意的是，该策略不会显著影响在洁净数据上的训练效果，从而在鲁棒性与洁净输入性能之间实现了理想的平衡。通过在多个基准数据集上针对不同攻击强度开展大量实验，我们证明该方法能在无需洁净真值监督的情况下，显著提升3DGS的鲁棒性。通过揭示并解决3D高斯泼溅技术中被忽视的脆弱性问题，本研究为构建更鲁棒、更安全的三维重建系统开辟了新路径。