A biologically inspired computational trust model for open multi-agent systems which is resilient to unwillingness and dishonesty in reporting of trust information

Abstract Selfish agents in highly dynamic and open multi-agent systems are usually unwilling to exchange information with each another and usually dishonest when doing so. Thus, the use of trust information provided by other agents makes most trust and reputation systems susceptible to various sorts of disinformation. To deal with this issue, we have proposed a computational trust model from the perspective of the trustee, inspired by aspects of the synaptic plasticity of the brain, in which the trustor does not choose a trustee to delegate a task, but it is the trustee who decides whether it has the skills to perform the task or not. The proposed trust model follows the decentralized approach, it is developed so as to deal with the requirements of highly dynamic and open multi-agent systems, and since agents do not exchange trust information, it is immune to various sorts of disinformation. We conducted an extensive empirical evaluation of our model comparing it with FIRE, an established trust and reputation model for open multi-agent systems, and observed that our model was able to perform consistently in various dynamic conditions, maintaining a high level of utility gain for the agents and being immune to unwillingness and dishonesty in reporting of trust information.