Application of differential privacy in smart building systems

Smart buildings are an important component of urban intelligence due to their efficient information management and engineering control. The large amount of data stored and shared in smart building systems may expose the privacy of users. This work deals with initial resource configuration information protection in a probabilistic automaton framework, using state-based differential privacy. For given two adjacent initial states, a verification method for state-based differential privacy is provided to verify whether an attacker can identify with which state the system is initialized. An enforcement method is proposed to ensure that two systems with adjacent initial states can generate observations with similar probability distributions. The examples in this paper show that applying differential privacy in smart building systems can effectively protect initial state information.