What is it about?
Cloud Computing is the distribution of computing resources on demand over Internet. A major issue of Cloud services are the problems regarding privacy and security of data and resources. In such environments Intrusion Detection Systems (IDS) comes in handy - they read huge chunks of data to find out attack patterns. But the learning process is very time consuming. Using feature selection methods, number of features can be reduced by eliminating redundant and irrelevant attributes from datasets. In this paper, a Penalty Reward based Ant Colony Optimization (PRACO) method for feature selection has been proposed.
Featured Image
Photo by RoonZ nl on Unsplash
Why is it important?
The proposed method uses a modified version of the Ant Colony Optimization (ACO) technique. The concept of penalty-reward is used to determine the direction of the artificial ants in each of the steps. After completing the first phase of feature selection, max-relevance and min-redundancy are applied to measure the interactions between selected features so that the feature subset can be further reduced. The results obtained after applying the proposed method on 10% KDD Cup 99, NSL-KDD and UNSW-NB15 datasets prove its effectiveness.
Perspectives
My co-authors and I put a lot of effort in developing the method. I hope the readers will be benefitted by this article and advancements will be made in the fields of Intrusion Detection System and Cloud security.
Partha Ghosh
Netaji Subhash Engineering College
Read the Original
This page is a summary of: Feature selection using PRACO method for IDS in cloud environment, Journal of Intelligent & Fuzzy Systems, September 2022, IOS Press,
DOI: 10.3233/jifs-212196.
You can read the full text:
Contributors
The following have contributed to this page
