论文标题
Infoshape：通过共同信息基于任务的神经数据塑造
InfoShape: Task-Based Neural Data Shaping via Mutual Information
论文作者
论文摘要
由于其在实践中的估计很难，将相互信息用作私人数据共享中的工具一直是一个悬而未决的挑战。在本文中，我们提出了基于任务的编码器InfoShape，旨在从培训数据中删除不必要的敏感信息，同时为特定的ML培训任务维护足够的相关信息。我们通过利用基于神经网络的共同信息估计器来实现这一目标，以衡量两个性能指标，隐私和实用性。在Lagrangian优化中一起使用它们，我们将单独的神经网络训练为有损的编码器。我们从经验上表明，InfoShape能够塑造编码的样本，以便在消除不必要的敏感信息的同时，为特定的下游任务提供信息。此外，我们证明下游模型的分类准确性与我们的效用和隐私措施有着有意义的联系。
The use of mutual information as a tool in private data sharing has remained an open challenge due to the difficulty of its estimation in practice. In this paper, we propose InfoShape, a task-based encoder that aims to remove unnecessary sensitive information from training data while maintaining enough relevant information for a particular ML training task. We achieve this goal by utilizing mutual information estimators that are based on neural networks, in order to measure two performance metrics, privacy and utility. Using these together in a Lagrangian optimization, we train a separate neural network as a lossy encoder. We empirically show that InfoShape is capable of shaping the encoded samples to be informative for a specific downstream task while eliminating unnecessary sensitive information. Moreover, we demonstrate that the classification accuracy of downstream models has a meaningful connection with our utility and privacy measures.
