首页> 外文会议>Annual IEEE-IFIP International Conference on Dependable Systems and Networks-Supplemental Volume >Neuraltran: Optimal Data Transformation for Privacy-Preserving Machine Learning by Leveraging Neural Networks
【24h】

Neuraltran: Optimal Data Transformation for Privacy-Preserving Machine Learning by Leveraging Neural Networks

机译:Neuraltran:利用神经网络实现隐私保护机器学习的最佳数据转换

获取原文

摘要

In this work, we develop a new data transformation technique to mediate privacy-preserving access to data while achieving machine learning (ML) tasks. Specifically, we first leverage mutual information in information theory to quantify the utility-providing information (corresponding to any ML task) and the privacy information (could be arbitrary information specified by the users). We further convert the optimization of utility-privacy tradeoff into training a novel neural network (named as NeuralTran) which consists of three modules: transformation module, utility module and privacy module. NeuralTran can be leveraged to automatically transform the input data to ensure that only utility-providing information is kept while the private information is removed. Through extensive experiments on real world datasets, we show the effectiveness of NeuralTran in balancing utility and privacy as well as its advantages over previous approaches.
机译:在这项工作中,我们开发了一种新的数据转换技术,以在实现机器学习(ML)任务的同时,调解隐私保护对数据的访问。具体而言,我们首先利用信息论中的互信息来量化实用程序提供的信息(对应于任何ML任务)和隐私信息(可以是用户指定的任意信息)。我们进一步将效用-隐私权衡的优化转换为训练一个新的神经网络(名为NeuralTran),该神经网络由三个模块组成:转换模块,效用模块和隐私模块。可以利用NeuralTran自动转换输入数据,以确保在删除私有信息的同时仅保留提供实用程序的信息。通过在现实世界数据集上进行的广泛实验,我们证明了NeuralTran在平衡实用程序和隐私方面的有效性及其相对于先前方法的优势。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号