Figure 5 shows an MSBN with three subnets [G.sub.0], [G.sub.1], [G.sub.2].
Once a multi-agent MSBN is constructed, agents may perform probabilistic inference by computing the query P(x|e), where x is any variable within the sub-domain of a group of agents, and e is the observations made by all the agents in the system.
This Bayesian network is sectioned into multiple subnets utilizing the rules for sound partitioning in MSBN .
The attack knowledge base was distributed among the agents in the workstations in the form of a MSBN as described earlier.
Section 3 provides some background information about Bayesian networks and MSBNs. Section 4 describes the architecture of the proposed system and the agents constituting the IDS.
In this section, some background information about Bayesian networks and MSBNs are given.
MSBNs provide a coherent framework for probabilistic reasoning in cooperative multi agent distributed interpretation systems (CMADISs) .
MSBNs form a coherent framework for probabilistic reasoning in CMADISs.