Open AccessIDSFS: A Signature Based Intrusion Detection System with High Pertinent Feature Selection Method
Author(s) -
S. Latha,
Sinthu Janita Prakash
Publication year - 2019
Publication title -
asian journal of computer science and technology
Language(s) - English
Resource type - Journals
eISSN - 2583-7907
pISSN - 2249-0701
DOI - 10.51983/ajcst-2019.8.2.2145
Subject(s) - computer science , intrusion detection system , feature selection , frame (networking) , host (biology) , network packet , benchmark (surveying) , data mining , signature (topology) , network security , selection (genetic algorithm) , variety (cybernetics) , anomaly based intrusion detection system , feature (linguistics) , matching (statistics) , artificial intelligence , computer security , computer network , statistics , ecology , linguistics , philosophy , geometry , mathematics , geodesy , biology , geography
Securing a network from the attackers is a challenging task at present as many users involve in variety of computer networks. To protect any individual host in a network or the entire network, some security system must be implemented. In this case, the Intrusion Detection System (IDS) is essential to protect the network from the intruders. The IDS have to deal with a lot of network packets with different characteristics. A signature-based IDS is a potential tool to understand former attacks and to define suitable method to conquest it in variety of applications. This research article elucidates the objective of IDS with a mechanism which combines the network and host-based IDS. The benchmark dataset for DARPA is considered to generate the IDS mechanism. In this paper, a frame work IDSFS – a signature-based IDS with high pertinent feature selection method is framed. This frame work consists of earlier proposed Feature Selection method (HPFSM), Artificial Neural Network for classification of nodes or packets in the network, then the signatures or attack rules are configured by implementing Association Rule mining algorithm and finally the rules are restructured using a pattern matching algorithm-Aho-Corasick to ease the rule checking. The metrics like number of features, classification accuracy, False Positive Rate (FPR), Precision, Number of rules, Running Time and Memory consumption are checked and proved the proposed frame work’s efficiency.