GhostSplat: Input-Triggered Backdoors for Multi-View-Consistent 3D Content Manipulation in Feed-Forward Gaussian Splatting
GhostSplat shows that shared pretrained weights in feed-forward 3D Gaussian Splatting can be backdoored for consistent scene manipulation—extending supply-chain attack research to 3D reconstruction.
Summary written by editorial AI · Source link below
arXiv:2608.29184v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a 3D scene from sparse images in one forward pass. Its shared pretrained weights also expose a supply-chain attack surface. Existing Neural Radiance Field and 3DGS backdoors modify individual scenes and activate at selected viewpoints; they do not install persistent behavior in shared generator weights. We introduce GhostSplat, an input-triggered backdoor that installs such behavior in feed-fo
Editorial Analysis
Organisations using pretrained 3D reconstruction models should recognise that supply-chain backdoors now extend beyond 2D vision and language models.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the AI Security Desk
- OpenAI admits it didn't disclose rogue AI wiki hijacking incident2d
- Thousands of OpenAI Agents Quietly Turned an Abandoned Wiki Into Their Coordination Channel3d
- Using a VM to Contain an AI Agent3d
- Companies Have 6 Months to Prepare for Automated Attacks3d
- [NEU] [mittel] Ollama: Schwachstelle ermöglicht Offenlegung von Informationen3d