A faster version of Louvain method for community detection for efficient modeling and analytics of cyber systems
Abstract
Cyber networks are complex networks with various hosts forming the entities of the network and the communication between them forming the edges of the network. Most cyber networks exhibit a community structure. A community is a group of nodes that are densely connected with each other as compared to other nodes in the network. Representing an IP network in the form of communities helps in viewing the network from different levels of granularity and makes the visualization of the network cleaner and more pleasing to the eye. This will help significantly in cyber attack detection in large scale cyber networks. In order to serve this purpose, it is important to retrieve the community structure fast, before the damage done by the attacker spreads and compromises the system. This research was an effort to bring about fast community detection of large cyber networks. The Louvain method, which is one of the most popular modularity optimization algorithms, was studied thoroughly and modified to make it faster, while preserving the quality of partitions at the same time.
Degree
M.S.
Advisors
Springer, Purdue University.
Subject Area
Computer Engineering|Computer science
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.