PARCo: an Agent for Context-Sensitive Reasoning and Decision-Making Regarding Privacy

Abstract

Privacy infringements in dynamic environments, such as online social networks and the Internet of Things, are still poorly addressed by traditional privacy regulations. Contextual Integrity (CI) has been proposed as an alternative definition of privacy, which describes privacy preservation in terms of appropriate information exchange, with respect to contextual norms. CI has inspired a number of approaches towards regulating appropriate information sharing in OSNs and the IoT. Nevertheless, due to its scale and heterogeneity, the IoT environment in particular, has been addressed by a limited number of efficient methods. The literature suggests that available approaches would benefit from a definition of contexts which can capture contexts' relations, allowing contexts' inference from fragmentary information. Furthermore, these approaches should display decision-making capabilities in partially observable and incomplete-information environments. This study proposes PARCo, a knowledge-based agent which reasons on its internal context representation implemented by way of an OWL ontology and subsequently uses argumentation to take an information sharing decision in the IoT environment. PARCo and its components are evaluated with respect to a selection of IoT scenarios and compared to a previous approach.