隐形攻击：通过密度引导的幻觉实现鲁棒的3D高斯溅射污染

摘要

诸如神经辐射场（NeRF）和三维高斯泼溅（3DGS）等三维场景表示方法，在视角合成领域取得了显著进展。随着这些方法的广泛应用，解决其潜在脆弱性变得至关重要。我们分析了3DGS对图像级投毒攻击的鲁棒性，并提出了一种新颖的密度引导投毒策略。该方法通过核密度估计（KDE）识别低密度区域，策略性地注入高斯点，从而在受污染视角中嵌入视角依赖的虚幻物体，这些物体清晰可见，而对未受影响的视角影响甚微。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，进一步增强攻击效果。我们提出了一种基于KDE的评估协议，系统性地评估攻击难度，为未来研究提供客观的基准测试。大量实验证明，相较于现有技术，我们的方法展现出更优的性能。项目页面：https://hentci.github.io/stealthattack/

English

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/

隐形攻击：通过密度引导的幻觉实现鲁棒的3D高斯溅射污染

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

摘要

Support