GaussLock embeds traps targeting position, scale, rotation, opacity, and color in 3D Gaussian models to degrade unauthorized fine-tunes while preserving authorized performance.
Non-transferable learn- ing: A new approach for model ownership verification and applicability authorization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
GaussLock embeds traps targeting position, scale, rotation, opacity, and color in 3D Gaussian models to degrade unauthorized fine-tunes while preserving authorized performance.