标题： StealthAttack：通过密度引导的幻觉进行鲁棒的3D高斯泼溅中毒 显示英文标题

标题： StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions

摘要： 3D场景表示方法如神经辐射场（NeRF）和3D高斯点云（3DGS）在新视角合成方面取得了显著进展。随着这些方法的普及，解决其脆弱性变得至关重要。我们分析了3DGS对图像级中毒攻击的鲁棒性，并提出了一种新颖的密度引导中毒方法。我们的方法通过核密度估计（KDE）识别低密度区域，有针对性地注入高斯点，嵌入从中毒视角明显可见的视角依赖性幻觉物体，同时对无辜视角的影响最小。此外，我们引入了一种自适应噪声策略以破坏多视角一致性，进一步提高攻击效果。我们提出了基于KDE的评估协议，系统地评估攻击难度，为未来研究提供客观基准。大量实验表明，我们的方法在性能上优于最先进的技术。项目页面：https://hentci.github.io/stealthattack/ 显示英文摘要

摘要： 3D scene representation methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have significantly advanced novel view synthesis. As these methods become prevalent, addressing their vulnerabilities becomes critical. We analyze 3DGS robustness against image-level poisoning attacks and propose a novel density-guided poisoning method. Our method strategically injects Gaussian points into low-density regions identified via Kernel Density Estimation (KDE), embedding viewpoint-dependent illusory objects clearly visible from poisoned views while minimally affecting innocent views. Additionally, we introduce an adaptive noise strategy to disrupt multi-view consistency, further enhancing attack effectiveness. We propose a KDE-based evaluation protocol to assess attack difficulty systematically, enabling objective benchmarking for future research. Extensive experiments demonstrate our method's superior performance compared to state-of-the-art techniques. Project page: https://hentci.github.io/stealthattack/