Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915559144161280 |
|---|---|
| author | Tan, Qifeng Yang, Shusen Ren, Xuebin Zhang, Yikai |
| author_facet | Tan, Qifeng Yang, Shusen Ren, Xuebin Zhang, Yikai |
| contents | Layer-wise Gaussian mechanisms (LGM) enhance flexibility in differentially private deep learning by injecting noise into partitioned gradient vectors. However, existing methods often rely on heuristic noise allocation strategies, lacking a rigorous understanding of their theoretical grounding in connecting noise allocation to formal privacy-utility tradeoffs. In this paper, we present a unified analytical framework that systematically connects layer-wise noise injection strategies with their implicit optimization objectives and associated privacy budget allocations. Our analysis reveals that several existing approaches optimize ill-posed objectives -- either ignoring inter-layer signal-to-noise ratio (SNR) consistency or leading to inefficient use of the privacy budget. In response, we propose a SNR-Consistent noise allocation strategy that unifies both aspects, yielding a noise allocation scheme that achieves better signal preservation and more efficient privacy budget utilization. Extensive experiments in both centralized and federated learning settings demonstrate that our method consistently outperforms existing allocation strategies, achieving better privacy-utility tradeoffs. Our framework not only offers diagnostic insights into prior methods but also provides theoretical guidance for designing adaptive and effective noise injection schemes in deep models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04232 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation Tan, Qifeng Yang, Shusen Ren, Xuebin Zhang, Yikai Machine Learning Layer-wise Gaussian mechanisms (LGM) enhance flexibility in differentially private deep learning by injecting noise into partitioned gradient vectors. However, existing methods often rely on heuristic noise allocation strategies, lacking a rigorous understanding of their theoretical grounding in connecting noise allocation to formal privacy-utility tradeoffs. In this paper, we present a unified analytical framework that systematically connects layer-wise noise injection strategies with their implicit optimization objectives and associated privacy budget allocations. Our analysis reveals that several existing approaches optimize ill-posed objectives -- either ignoring inter-layer signal-to-noise ratio (SNR) consistency or leading to inefficient use of the privacy budget. In response, we propose a SNR-Consistent noise allocation strategy that unifies both aspects, yielding a noise allocation scheme that achieves better signal preservation and more efficient privacy budget utilization. Extensive experiments in both centralized and federated learning settings demonstrate that our method consistently outperforms existing allocation strategies, achieving better privacy-utility tradeoffs. Our framework not only offers diagnostic insights into prior methods but also provides theoretical guidance for designing adaptive and effective noise injection schemes in deep models. |
| title | Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.04232 |