PAC: Privacy-preserving Arrhythmia Classification with neural networks

Mansouri, Mohamad; Bozdemir, Beyza; Önen, Melek; Ermis, Orhan
FPS 2019, 12th International Symposium on Foundations and Practice of Security, November 5-7, 2019, Toulouse, France / Also published in LNCS, Vol. 12056

Best Paper Award

In this paper, we propose to study privacy concerns raised by the analysis of Electro CardioGram (ECG) data for arrhythmia classification. We propose a solution named PAC that combines the use of Neural Networks (NN) with secure two-party computation in order to enable an efficient NN prediction of arrhythmia without discovering the actual ECG data. To achieve a good trade-off between privacy, accuracy, and efficiency, we first build a dedicated NN model which consists of two fully connected layers and one activation layer as a square function. The solution is implemented with the ABY framework. PAC also supports classifications in batches. Experimental results show an accuracy of 96.34% which outperforms existing solutions.


DOI
HAL
Type:
Conférence
City:
Toulouse
Date:
2019-11-04
Department:
Sécurité numérique
Eurecom Ref:
6046
Copyright:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in FPS 2019, 12th International Symposium on Foundations and Practice of Security, November 5-7, 2019, Toulouse, France / Also published in LNCS, Vol. 12056 and is available at : https://doi.org/10.1007/978-3-030-45371-8_1

PERMALINK : https://www.eurecom.fr/publication/6046