Full Program

Large Scale Cyber Security Log Classification Using Semi-Supervised Clustering

Summary:

In this paper we present semi-supervised approach developed with the aim addressing the challenge of large-scale cyber security log entry classification that is faced by organizations that lack significant in-house expertise. We applied two well established unsupervised clustering approaches to the Curtin Dataset, and we describe in detail the results obtained using a range of experimental setups. Moreover, in addition to the results, we provide a new large-scale cyber security dataset that can be used in cyber security related research.

Author(s):

Peng Cai    
Curtin University
Australia

Mihai Lazarescu    
Curtin University
Australia

Sie Teng Soh    
Curtin University
Australia

Reza Ryan    
Curtin University
Australia