论文信息 - Towards Dynamic End-to-End Privacy Preserving Data Classification

Towards Dynamic End-to-End Privacy Preserving Data Classification

In this paper we present DAPPLE, a standalone End-to-End privacy preserving data classification service. It allows incremental decision tree learning over encrypted training data continuously sent by multiple data owners, without having access to the actual content of this data. In the same time, the learnt classification model is used to respond to encrypted classification queries while preserving the privacy of the query, the output corresponding to it and the model itself.

[1] Francisco Javier González-Serrano,et al. Training Support Vector Machines with privacy-protected data , 2017, Pattern Recognit..

[2] Geoff Hulten,et al. Mining high-speed data streams , 2000, KDD '00.

[3] Hiroshi Tsuda,et al. Privacy-Preserving Distributed Decision Tree Learning with Boolean Class Attributes , 2013, 2013 IEEE 27th International Conference on Advanced Information Networking and Applications (AINA).

[4] Boris Murmann,et al. Approximate SRAM for Energy-Efficient, Privacy-Preserving Convolutional Neural Networks , 2017, 2017 IEEE Computer Society Annual Symposium on VLSI (ISVLSI).

[5] Ximeng Liu,et al. An Efficient Privacy-Preserving Outsourced Calculation Toolkit With Multiple Keys , 2016, IEEE Transactions on Information Forensics and Security.

[6] Shafi Goldwasser,et al. Machine Learning Classification over Encrypted Data , 2015, NDSS.

[7] Michael Naehrig,et al. CryptoNets: applying neural networks to encrypted data with high throughput and accuracy , 2016, ICML 2016.

[8] Jin Li,et al. Privacy-preserving Naive Bayes classifiers secure against the substitution-then-comparison attack , 2018, Inf. Sci..

[9] Zhang Peng. Privacy Preserving Naive Bayes Classification , 2007 .