SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography
This work addresses privacy protection for 3D assets in applications like real-time rendering, though it appears incremental as it builds on prior GS steganography solutions.
The paper tackled the problem of securing 3D Gaussian Splatting (3DGS) assets by proposing SecureGS, a steganography framework that embeds hidden data in anchor point features, resulting in significant improvements in rendering fidelity, speed, and security compared to existing methods.
3D Gaussian Splatting (3DGS) has emerged as a premier method for 3D representation due to its real-time rendering and high-quality outputs, underscoring the critical need to protect the privacy of 3D assets. Traditional NeRF steganography methods fail to address the explicit nature of 3DGS since its point cloud files are publicly accessible. Existing GS steganography solutions mitigate some issues but still struggle with reduced rendering fidelity, increased computational demands, and security flaws, especially in the security of the geometric structure of the visualized point cloud. To address these demands, we propose a SecureGS, a secure and efficient 3DGS steganography framework inspired by Scaffold-GS's anchor point design and neural decoding. SecureGS uses a hybrid decoupled Gaussian encryption mechanism to embed offsets, scales, rotations, and RGB attributes of the hidden 3D Gaussian points in anchor point features, retrievable only by authorized users through privacy-preserving neural networks. To further enhance security, we propose a density region-aware anchor growing and pruning strategy that adaptively locates optimal hiding regions without exposing hidden information. Extensive experiments show that SecureGS significantly surpasses existing GS steganography methods in rendering fidelity, speed, and security.