摘要：AbstractIn this paper, we consider the security problem of opinion dynamics in attack-defense environment in social networks. First, we propose an opinion dynamics model, which is composed by attackers, defenders and the masses. In the proposed model, a set of attackers controlled by the agent with hostile opinion sends malicious opinion to their neighbors with a certain probability, and the defenders are activated by the agent with right opinion at a triggering time to lead the opinions of the masses to a safe zone. Second, we provide a sufficient condition to ensure the convergence of the expected opinions of the system. We also give the method to seek a lower bound of the opinions spread by the defenders at each time step while keeping the opinions in safe situation. Finally, we provide a numerical example to verify the main results.
