Task-aware Privacy Preservation for Multi-dimensional Data
Task-aware Privacy Preservation for Multi-dimensional Data
复制标题
DOI：
--
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Jiangnan Cheng;A. Tang;Sandeep Chinchali
中科院分区：
文献类型：
--
作者：
Jiangnan Cheng;A. Tang;Sandeep Chinchali
本地差分隐私（LDP）可以用于匿名化更丰富的用户数据属性，这些属性将被输入到复杂的机器学习（ML）任务中。然而，今天的LDP方法在很大程度上是与任务无关的，并且经常导致严重的性能损失——它们只是根据给定的隐私预算向所有数据属性注入噪声，而不管哪些特征与最终任务最相关。在本文中，我们讨论了如何通过考虑任务感知隐私保护问题来显著提高多维用户数据的最终任务性能。关键思想是使用编码器-解码器框架来学习（并匿名化）与任务相关的用户数据潜在表示。我们得到了具有均方误差（MSE）任务损失的线性设置的解析近似最优解。我们还通过基于梯度的学习算法提供了一般非线性情况的近似解。大量的实验表明，与具有相同隐私保证级别的标准基准LDP方法相比，我们的任务感知方法显着提高了最终任务准确性。
Local differential privacy (LDP) can be adopted to anonymize richer user data attributes that will be input to sophisticated machine learning (ML) tasks. However, today’s LDP approaches are largely task-agnostic and often lead to severe performance loss – they simply inject noise to all data attributes according to a given privacy budget, regardless of what features are most relevant for the ultimate task. In this paper, we address how to significantly improve the ultimate task performance with multi-dimensional user data by considering a task-aware privacy preservation problem. The key idea is to use an encoder-decoder framework to learn (and anonymize) a task-relevant latent representation of user data. We obtain an analytical near-optimal solution for the linear setting with mean-squared error (MSE) task loss. We also provide an approximate solution through a gradient-based learning algorithm for general nonlinear cases. Extensive experiments demon-strate that our task-aware approach significantly improves ultimate task accuracy compared to standard benchmark LDP approaches with the same level of privacy guarantee.