On the identity anonymization of high-dimensional rating data

Abstract

We study the challenges of protecting the privacy of individuals in a large public survey rating data. The survey rating data usually contains both ratings of sensitive and non-sensitive issues. The ratings of sensitive issues involve personal privacy. Although the survey participants do not reveal any of their ratings, their survey records are potentially identifiable by using information from other public sources. None of the existing anonymization principles (e.g. k-anonymity, l-diversity, etc.) can effectively prevent such breaches in large survey rating data sets. In this paper, we tackle the problem by defining a principle called (k, epsilon, l)-anonymity. The principle requires that, for each transaction t in the given survey rating data T, at least (k − 1) other transactions in T must have ratings similar to t, where the similarity is controlled by ε and the standard deviation of sensitive ratings is at least l. We propose a greedy approach to anonymize the survey rating data that scales almost linearly with the input size, and we apply the method to two real-life data sets to demonstrate their efficiency and practical utility.