PulseAugur
实时 09:31:56
English(EN) ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages

新的ComplicitSplat攻击利用3D高斯溅射进行对抗性图像操纵

研究人员开发了一种名为ComplicitSplat的新型黑盒攻击方法,该方法利用3D高斯溅射(3DGS)将对抗性内容嵌入图像中。该技术创建了特定视角的伪装,其中恶意纹理或颜色仅从特定角度可见,而无需访问目标模型的架构或权重。ComplicitSplat已成功攻击了包括单阶段、多阶段和基于Transformer的模型在内的各种目标检测器,对自动导航和机器人等应用构成了新的安全风险。 AI

影响 这项研究突显了使用3D高斯溅射的计算机视觉系统中的一种新漏洞,可能影响自动导航等关键领域的AI应用的安全性与可靠性。

排序理由 该集群描述了一种新颖的攻击方法,该方法在arXiv上发表的学术论文中有详细介绍。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的ComplicitSplat攻击利用3D高斯溅射进行对抗性图像操纵

本文如何被排名

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一种新颖的攻击方法,该方法在arXiv上发表的学术论文中有详细介绍。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Matthew Hull, Haoyang Yang, Pratham Mehta, Mansi Phute, Aeree Cho, Haorang Wang, Matthew Lau, Wenke Lee, Wilian Lunardi, Martin Andreoni, Duen Horng Chau ·

    ComplicitSplat:下游模型易受3D高斯溅射伪装的黑盒攻击

    arXiv:2508.11854v3 Announce Type: replace-cross Abstract: As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause harm? We introduce ComplicitSplat, the firs…