A Survey on Automatic Abnormalities Monitoring System for Log Files using Machine Learning
Main Article Content
Abstract
Attacks on a system's security are growing increasingly common since cyber criminals make a living out of system flaw exploitation. There is revenue loss and serious business and government impact. Widely used techniques to overcome these hazards are Signature recognition and anomaly detection, though these techniques are a good way to secure a system, they are unable to detect real time or modern attacks. The objective of this research is to survey different literature that uses security analytics to distinguish between malicious and normal activity. It also aims at creating a model that applies machine learning (ML) techniques to various log files which are at the server side with its nature as heterogeneous and can identify such users who are not given the access to these files using security analytics. The work proposes to develop and evaluate making use of the numerous production log files available on the website data.gov.in released under National Data Sharing and Accessibility Policy (NDSAP). This study establishes a foundation on which future research in this field may be constructed.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.