A Comprehensive Review and Meta-Analysis on Applications of Machine Learning Techniques in Intrusion Detection

Manojit Chattopadhyay, Rinku Sen, Sumeet Gupta


Securing a machine from various cyber-attacks has been of serious concern for researchers, statutory bodies such as governments, business organizations and users in both wired and wireless media. However, during the last decade, the amount of data handling by any device, particularly servers, has increased exponentially and hence the security of these devices has become a matter of utmost concern. This paper attempts to examine the challenges in the application of machine learning techniques to intrusion detection. We review different inherent issues in defining and applying the machine learning techniques to intrusion detection. We also attempt to identify the best technological solution for the changing usage pattern by comparing the different machine learning techniques on different datasets and summarizing their performance using various performance metrics. This paper highlights the research challenges and future trends of intrusion detection in dynamic scenarios of intrusion detection problems in diverse network technologies.


Intrusion detection; machine learning; soft computing; dataset; performance metrics; cyber-infrastructure; mobile communications; mobile systems; security; wireless technology

Full Text:


DOI: http://dx.doi.org/10.3127/ajis.v22i0.1667

License URL: https://creativecommons.org/licenses/by-nc/3.0/au/

Creative Commons License
ISSN: Online: 1326-2238 Hard copy: 1449-8618
This work is licensed under a Creative Commons Attribution-NonCommercial Licence. Uses the Open Journal Systems. Web design by TomW.