PEOPL：利用公共标签表征私有编码的开放数据集
PEOPL: Characterizing Privately Encoded Open Datasets with Public Labels
AI总结：
针对数据共享中的隐私泄露问题，本文提出PEOPL方法，利用随机变换对敏感数据进行编码，引入信息论分数量化隐私与效用，并证明该方案在抵御计算攻击的同时保持了与原始样本基线相当的预测准确率，且支持多机构协作训练。
摘要：
允许组织共享其数据用于训练机器学习（ML）模型且不发生无意的敏感信息泄露，在实践中仍是一个悬而未决的难题。针对这一开放问题，一种极具前景的技术是在编码后的数据上训练模型。我们的方法被称为“具有公共标签的私有编码开放数据集”（PEOPL），利用一类特定随机构造的变换来对敏感数据进行编码。组织发布其随机编码后的数据及相关的原始标签用于ML训练，此训练过程在不知晓编码具体实现的情况下进行。我们研究了该问题的几个重要方面：首先，我们引入了隐私和效用的信息论分数，用于量化访问已发布编码数据的非忠实用户（如攻击者）与忠实用户（如模型开发者）的平均表现。随后，我们从理论上刻画了构建编码方案族的基本原语，这些原语为使用随机深度神经网络提供了理论动机。在实验方面，我们将这种随机编码方案及一种线性方案与一系列计算攻击进行了性能比较，并证明了该方案能取得与原始样本基线相当的预测准确率。此外，我们还展示了使用独立随机编码器的多个机构能够相互协作，从而训练出性能更优的ML模型。
英文摘要：
Allowing organizations to share their data for training of machine learning (ML) models without unintended information leakage is an open problem in practice. A promising technique for this still-open problem is to train models on the encoded data. Our approach, called Privately Encoded Open Datasets with Public Labels (PEOPL), uses a certain class of randomly constructed transforms to encode sensitive data. Organizations publish their randomly encoded data and associated raw labels for ML training, where training is done without knowledge of the encoding realization. We investigate several important aspects of this problem: We introduce information-theoretic scores for privacy and utility, which quantify the average performance of an unfaithful user (e.g., adversary) and a faithful user (e.g., model developer) that have access to the published encoded data. We then theoretically characterize primitives in building families of encoding schemes that motivate the use of random deep neural networks. Empirically, we compare the performance of our randomized encoding scheme and a linear scheme to a suite of computational attacks, and we also show that our scheme achieves competitive prediction accuracy to raw-sample baselines. Moreover, we demonstrate that multiple institutions, using independent random encoders, can collaborate to train improved ML 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。
