The information bottleneck (IB) approach, initially introduced by [1] to assess the compression-relevance tradeoff for a remote source coding problem in communication, quickly gains popularity recently in its application to modern machine learning (ML). Unlike the use of most - if not all - IB in the literature, either for the analysis of, say deep neural networks, or as an optimization objective, in this paper, we propose to address the secrecy issue in ML, by considering the fundamental model of Gaussian mixture classification. We derive, for the first time, closed-form achievable bounds for the IB problem under the above setting, and provide precise characterization of the underlying performance-secrecy tradeoff. Experiments on both synthetic and real-world data are performed to confirm the satisfactory performance of the proposed scheme.

翻译：信息瓶颈（IB）方法最初由文献[1]引入，用于评估通信中远程信源编码问题的压缩-相关性权衡，近年来因其在现代机器学习（ML）中的应用而迅速获得广泛关注。与现有文献中大多数（若非全部）将IB用于深度神经网络分析或作为优化目标的做法不同，本文通过考虑高斯混合分类的基本模型，提出解决ML中的保密性问题。我们首次导出了上述设定下IB问题的闭式可达界，并精确刻画了其性能-保密性权衡的内在特性。基于合成数据与真实数据的实验均验证了所提方案的满意性能。