通过多项式扰动实现多用户隐私保护，无需梯度加噪。
Stabilization of Perturbed Loss Function: Differential Privacy without Gradient Noise
- 用泰勒展开多项式近似损失函数并扰动系数实现隐私保护。
- 相比DP-SGD，重建准确率高3.5%，训练时间减少57.2%。
- 适合无线体感网络等存在噪声和异构数据的多用户场景。
我们提出SPOF（扰动损失函数稳定化），一种面向多用户本地差分隐私（LDP）的差分隐私训练机制。SPOF对模型训练损失函数的稳定泰勒多项式近似进行扰动，每位用户的私有化通过向多项式系数添加校准噪声实现。与需要在损失梯度中注入噪声的基于梯度的方法（如DP-SGD）不同，SPOF无需梯度加噪，从而提升了计算效率与训练稳定性。该方法天然支持所有用户的同时隐私保障。此外，SPOF对训练过程中的环境噪声具有鲁棒性，在用户输入受扰时仍能保持稳定性能。我们在包含异构用户数据与体感传感器随机信道噪声的无线体域网（WBAN）场景中，将SPOF与多用户扩展版DP-SGD进行了对比。结果表明，SPOF平均可提升3.5%的重建准确率，并将平均训练时间降低57.2%，在多用户环境中展现出更优的隐私-效用权衡。
原文摘要 · Abstract (English)
We propose SPOF (Stabilization of Perturbed Loss Function), a differentially private training mechanism intended for multi-user local differential privacy (LDP). SPOF perturbs a stabilized Taylor expanded polynomial approximation of a model's training loss function, where each user's data is privatized by calibrated noise added to the coefficients of the polynomial. Unlike gradient-based mechanisms such as differentially private stochastic gradient descent (DP-SGD), SPOF does not require injecting noise into the gradients of the loss function, which improves both computational efficiency and stability. This formulation naturally supports simultaneous privacy guarantees across all users. Moreover, SPOF exhibits robustness to environmental noise during training, maintaining stable performance even when user inputs are corrupted. We compare SPOF with a multi-user extension of DP-SGD, evaluating both methods in a wireless body area network (WBAN) scenario involving heterogeneous user data and stochastic channel noise from body sensors. Our results show that SPOF achieves, on average, up to 3.5% higher reconstruction accuracy and reduces mean training time by up to 57.2% compared to DP-SGD, demonstrating superior privacy-utility trade-offs in multi-user environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。