A stochastic evolutionary coalition game model of secure and dependable virtual service in Sensor-Cloud

The figure shows an attack model for VSSNs, which includes end users, malicious users, physical sensors, and virtual sensors. The physical sensor network is mapped to VSSNs. Malicious users attack virtual-sensor-service nodes by scanning service vulnerabilities and attacking virtual capacities in order to damage service composites and reduce the service reliability. Virtual-sensor-service nodes' adaptive defense optimization problem can be modeled by several representations such as coalition players' decision problem (MCDP), the stochastic and evolutionary coalition game, and interactive partially observable Markov decision process for attackers and defenders. A number of attackers and defenders interact with virtual sensor service at discrete time stages. At each time stage, every player takes a defense action, which makes the virtual sensor service transit to the next state. At the next time stage, each player receives a local observation of the virtual capacity. State transition and update learning model the dynamics of the service reliability, while the accumulative payoff by self-learning optimizes the value of taking action in a particular state in coalitions.