Work

On the Protection of Private Information in Machine Learning Systems: Two Recent Approches

Year: 2017
Type: conference-paper
Abstract: The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving privacy. However, older ideas about privacy may well remain valid and useful. This note reviews two recent works on privacy in the light of the wisdom of some of the early literature, in particular the principles distilled by Saltzer and Schroeder in the 1970s.
Language: English
Open Access status: green
OpenAlex ID: W2751384916
FWCI: 3.071
Cites: 43
Cited by: 52
Related to: 9