Classification under local differential privacy

Despite the long history of this problem there are still many open pro blems and it remains an active topic of research. Recent work has focused on weake ning commonly-made assumptions [ 4 ], studying situations in which the training data comes froma different distribution to the test data [ 3, 5 ], and making predictions under constraints on allowable classifiers [ 16 ]. In recent years, it has become clear that in certain studies t here is a need to preserve the privacy of the individuals whose data is collected . As a way of formalising the problem, the framework of differential privacy, see [ 9 ] and [ 10 ], has prevailed as a natural solution.