Open Access Open Access  Restricted Access Subscription or Fee Access

Database Intrusion Detection Using Genetic Support Vector Fuzzy Clustering Learning Model

Anitarani Brahma, Suvasini Panigrahi



The rapid development of computer networks and increasing dependency of almost all companies and government agencies on Internet and cloud computing lead to the problem of stability and security like intrusions in several forms which can cause huge loss to these organizations. During recent years, disaster in data due to intrusions has dramatically increased. The hindrance of such intrusions is entirely dependent on their detection part which can be possible through a high-performance based intrusion detection system in database which has higher accuracy rate and negligible false positive rate. As part of funded effort in database security, soft computing proven to be capable of creating a system capable of detecting and characterizing anomalous behaviour which is composed of evolutionary computing tools with artificial neural networks and/or fuzzy logic. In this progression, here we present a Database Intrusion Detection System, by applying Genetic Algorithm for feature extraction and Fuzzy clustering and Support Vector Machines are used for detection purpose to efficiently detect insider threat with a reasonable false positive rate.

Keywords: Genetic Algorithm, Support Vector Machine, Fuzzy Clustering, Database Intrusion Detection System

Cite this Article

Anitarani Brahma, SuvasiniPanigrahi. Database Intrusion Detection Using Genetic Support Vector Fuzzy Clustering Learning Model. Journal of Artificial Intelligence Research & Advances. 2019; 6(2): 32–40p.

Full Text:



  • There are currently no refbacks.