The application of Bayesian statistics in measuring anonymity

Abstract

There are numerous efforts to measure the degree of anonymity. Among which the entropy anonymity is a popular one. However in practice entropy anonymity is hardly used because one of its assumptions is difficult to meet. In this paper we propose a method to tackle this problem. Our method is based on Bayesian statistics and can be used to compare the entropy anonymity of different anonymous communication systems. We use this method to analyze Threshold Mix to show its effectiveness and usefulness.