Using extreme learning machine for intrusion detection in a big data environment
Junlong Xiang, Magnus Westerlund, Dušan Sovilj, Göran Pulkkis · 2014
Extending state-of-the-art machine learning algorithms to highly scalable (big data) analysis environments is crucial for the handling of authentic datasets in Intrusion Detection Systems (IDS). Traditional supervised learning methods are considered to be too slow for use in these environments. Therefore, we propose the use of Extreme Learning Machine (ELM) for detecting network intrusion attempts. We show they hold great promise for the field by employing a MapReduce based variant evaluated on the open source tool Hadoop.