Towards context adaptive privacy decisions in ubiquitous computing

In ubiquitous systems control of privacy settings will be increasingly difficult due to the pervasive nature of sensing and communication capabilities. We identify challenges for privacy decisions in ubiquitous systems and propose a system for in situ privacy decision support. When context changes occur, the system adapts a user's privacy preferences to the new situation. As a consequence, recommendations can be offered to the user or sharing behavior can be automatically adjusted to help the user maintain a desired level of privacy. The system learns from user interaction and behavior to improve decision accuracy. In this paper, we outline the main components of our system and illustrate its operation with an ambient assisted living use case