$S^2$NeRF: Privacy-preserving Training Framework for NeRF
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917767335116800 |
|---|---|
| author | Zhang, Bokang Zhang, Yanglin Zhang, Zhikun Yang, Jinglan Huang, Lingying Wu, Junfeng |
| author_facet | Zhang, Bokang Zhang, Yanglin Zhang, Zhikun Yang, Jinglan Huang, Lingying Wu, Junfeng |
| contents | Neural Radiance Fields (NeRF) have revolutionized 3D computer vision and graphics, facilitating novel view synthesis and influencing sectors like extended reality and e-commerce. However, NeRF's dependence on extensive data collection, including sensitive scene image data, introduces significant privacy risks when users upload this data for model training. To address this concern, we first propose SplitNeRF, a training framework that incorporates split learning (SL) techniques to enable privacy-preserving collaborative model training between clients and servers without sharing local data. Despite its benefits, we identify vulnerabilities in SplitNeRF by developing two attack methods, Surrogate Model Attack and Scene-aided Surrogate Model Attack, which exploit the shared gradient data and a few leaked scene images to reconstruct private scene information. To counter these threats, we introduce $S^2$NeRF, secure SplitNeRF that integrates effective defense mechanisms. By introducing decaying noise related to the gradient norm into the shared gradient information, $S^2$NeRF preserves privacy while maintaining a high utility of the NeRF model. Our extensive evaluations across multiple datasets demonstrate the effectiveness of $S^2$NeRF against privacy breaches, confirming its viability for secure NeRF training in sensitive applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_01661 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | $S^2$NeRF: Privacy-preserving Training Framework for NeRF Zhang, Bokang Zhang, Yanglin Zhang, Zhikun Yang, Jinglan Huang, Lingying Wu, Junfeng Cryptography and Security Computer Vision and Pattern Recognition Machine Learning Neural Radiance Fields (NeRF) have revolutionized 3D computer vision and graphics, facilitating novel view synthesis and influencing sectors like extended reality and e-commerce. However, NeRF's dependence on extensive data collection, including sensitive scene image data, introduces significant privacy risks when users upload this data for model training. To address this concern, we first propose SplitNeRF, a training framework that incorporates split learning (SL) techniques to enable privacy-preserving collaborative model training between clients and servers without sharing local data. Despite its benefits, we identify vulnerabilities in SplitNeRF by developing two attack methods, Surrogate Model Attack and Scene-aided Surrogate Model Attack, which exploit the shared gradient data and a few leaked scene images to reconstruct private scene information. To counter these threats, we introduce $S^2$NeRF, secure SplitNeRF that integrates effective defense mechanisms. By introducing decaying noise related to the gradient norm into the shared gradient information, $S^2$NeRF preserves privacy while maintaining a high utility of the NeRF model. Our extensive evaluations across multiple datasets demonstrate the effectiveness of $S^2$NeRF against privacy breaches, confirming its viability for secure NeRF training in sensitive applications. |
| title | $S^2$NeRF: Privacy-preserving Training Framework for NeRF |
| topic | Cryptography and Security Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2409.01661 |