arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.22282cs.CRcs.LGstat.APstat.MEstat.ML
收藏

通过公共二阶矩实现无界数据的差分隐私截断

Differentially Private Truncation of Unbounded Data via Public Second Moments

School of Mathematics, Northwest University(西北大学数学学院)

Zilong Cao, Xuan Bi, Hai Zhang

AI总结:

本文提出PMT方法,通过利用公开二阶矩信息对无界数据进行差分隐私截断,提升模型的隐私保护和稳定性。

摘要:

在人工智能时代,数据隐私至关重要,差分隐私(DP)是其中的一种黄金解决方案。然而,DP通常仅适用于具有有界底层分布的数据。我们通过利用少量公开数据的二阶矩信息来解决这一限制。我们提出了Public-moment-guided Truncation(PMT),它利用公开的二阶矩矩阵对私有数据进行转换,并应用一种基于非隐私量(数据维度和样本量)的原理化截断。这种转换产生了一个良好的条件二阶矩矩阵,使其能够通过显著增强的抗DP噪声能力进行反向运算。此外,我们通过惩罚和广义线性回归展示了PMT的应用。具体而言,我们设计了新的损失函数和算法,确保在转换空间中的解能够映射回原始领域。我们通过理论误差界、鲁棒性保证和收敛结果证明了模型的DP估计改进,这些改进归因于PMT的条件效应。在合成和真实数据集上的实验表明,PMT显著提高了DP模型的准确性和稳定性。

英文摘要:

Data privacy is important in the AI era, and differential privacy (DP) is one of the golden solutions. However, DP is typically applicable only if data have a bounded underlying distribution. We address this limitation by leveraging second-moment information from a small amount of public data. We propose Public-moment-guided Truncation (PMT), which transforms private data using the public second-moment matrix and applies a principled truncation whose radius depends only on non-private quantities: data dimension and sample size. This transformation yields a well-conditioned second-moment matrix, enabling its inversion with a significantly strengthened ability to resist the DP noise. Furthermore, we demonstrate the applicability of PMT by using penalized and generalized linear regressions. Specifically, we design new loss functions and algorithms, ensuring that solutions in the transformed space can be mapped back to the original domain. We have established improvements in the models' DP estimation through theoretical error bounds, robustness guarantees, and convergence results, attributing the gains to the conditioning effect of PMT. Experiments on synthetic and real datasets confirm that PMT substantially improves the accuracy and stability of DP models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑