APN model construction for malicious email detection

Abstract

Recently, associative Petri nets (APNs) have been attracted in knowledge representation and modeling of expert systems. However, it is a challenge in transferring from a complex system to an APNs model. Moreover, the domain knowledge and relationship finding between processes has increased in difficulty and complexity in expert and intelligence systems. This paper addresses this issue by proposing a novel systematic procedure to guide the analyst in creating decision support models. The proposed construction algorithm can not only reduce the effort of construction but also can easily implement for knowledge representation. It can give a summary to describe all states but also simplify the reasoning process. An example of malicious email detection is presented to provide empirical evidence in the utility of the systematic procedure of associative Petri net model construction. Experimental result shows that our constructed APN model outperforms than other methods.