In a society where digital data has become ubiquitous and has been projected to continue in this trajectory for the foreseeable future, machine learning has become a dependable tool to aid in analyzing these big datasets. However, where the data or machine learning algorithms are considered to be privacy-sensitive, one is then faced with the challenge of preserving the utility of machine learning in a privacy-preserving setting. In this paper, we focus on a use case where decentralized parties have privately owned machine learning algorithms, and would want to jointly generate a public model while not violating the privacy of their individual models, and data. We present ECONoMy: a privacy-preserving protocol that supports collaborative learning using an ensemble technique. Set in an honest-but-curious security model, ECONoMy is lightweight and provides efficiency and privacy in settings with large participant such as with IoT devices.

Original languageEnglish
Title of host publication2019 IEEE 30th International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC Workshops 2019
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages7
ISBN (Electronic)9781538693582
DOIs
Publication statusPublished - 1 Sep 2019
Event30th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC Workshops 2019 - Istanbul, Turkey
Duration: 8 Sep 2019 → …

Conference

Conference30th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC Workshops 2019
CountryTurkey
CityIstanbul
Period8/09/19 → …

    Research areas

  • Collaborative, Ensemble, Machine Learning, Masking, Privacy-Preserving

ID: 66953875