Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Understanding Semantic Perturbations on In-Processing Generative Image Watermarks
Anirudh Nakra, Min Wu
The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authentication. In-processing watermarking,…
cs.CR2026
Position: 3D Gaussian Splatting Watermarking Should Be Scenario-Driven and Threat-Model Explicit
Yangfan Deng, Anirudh Nakra, Min Wu
3D content acquisition and creation are expanding rapidly in the new era of machine learning and AI. 3D Gaussian Splatting (3DGS) has become a promising high-fidelity and real-time…