Semi-autonomous, context-aware, agent using behaviour modelling and reputation systems to authorize data operation in the Internet of Things

Abstract: In this paper we address the issue of gathering the "informed consent" of an end user in the Internet of Things. We start by evaluating the legal importance and some of the problems linked with this notion of informed consent in the specific context of the Internet of Things. From this assessment we propose an approach based on a semi-autonomous, rule based agent that centralize all authorization decisions on the personal data of a user and that is able to take decision on his behalf. We complete this initial agent by integrating context-awareness, behavior modeling and community based reputation system in the algorithm of the agent. The resulting system is a "smart" application, the "privacy butler" that can handle data operations on behalf of the end-user while keeping the user in control. We finally discuss some of the potential problems and improvements of the system.