Adversarial Contract Design for Private Data Commercialization

Abstract

The proliferation of data collection and machine learning techniques has created an opportunity for commercialization of private data by data aggregators. In this paper, we study this data monetization problem as a mechanism design problem, specifically using a contract-theoretic approach. Our proposed adversarial contract design framework provides a fundamental extension to the classic contract theory set-up in order to account for the heterogeneity in honest buyers' demands for data, as well as the presence of adversarial buyers who may purchase data to compromise its privacy. We propose the notion of Price of Adversary $(PoAdv)$ to quantify the effects of adversarial users on the data seller's revenue, and provide bounds on the $PoAdv$ for various classes of adversary utility. We also provide a fast approximate technique to compute contracts in the presence of adversaries.