Attacks on privacy and deFinetti's theorem

In this paper we present a method for reasoning about privacy using the concepts of exchangeability and deFinetti's theorem. We illustrate the usefulness of this technique by using it to attack a popular data sanitization scheme known as Anatomy. We stress that Anatomy is not the only sanitization scheme that is vulnerable to this attack. In fact, any scheme that uses the random worlds model, i.i.d. model, or tuple-independent model needs to be re-evaluated. The difference between the attack presented here and others that have been proposedin the past is that we do not need extensive background knowledge. An attacker only needs to know the nonsensitive attributes of one individual in the data, and can carry out this attack just by building a machine learning model over the sanitized data. The reason this attack is successful is that it exploits a subtle flaw in the way prior work computed the probability of disclosure of a sensitive attribute. We demonstrate this theoretically, empirically, and with intuitive examples. We also discuss how this generalizes to many other privacy schemes.