期刊名称:International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN:2320-9798
电子版ISSN:2320-9801
出版年度:2017
卷号:5
期号:2
页码:1936
DOI:10.15680/IJIRCCE.2017.0502158
出版社:S&S Publications
摘要:Nowadays the security issues of Network become more sharp and urgent, in order to improve theinitiative of Network security protection and the validity. This paper presents a new proactive security algorithm namedhoneypot using PCA algorithm to expand the network topology space and confuse the attacker, Network is beingconfronted currently and the common attack tools, methods and rules, so as to amend the network security architectureaccording to specific situations, to revised security management principles of all levels, to adjust the firewallconfiguration to enhance the holistic security of Network.Most current anomaly Intrusion Detection Systems (IDSs) detect computer network behaviour as normal or abnormalbut cannot identify the type of attacks. Moreover, most current intrusion detection methods cannot process largeamounts of audit data for real-time operation. In this paper, we propose a novel method for intrusion identification incomputer networks based on Principal Component Analysis (PCA). PCA is employed to reduce the dimensionality ofthe data vectors and identification is handled in a low dimensional space with high efficiency and low use of systemresources. The normal behaviour is profiled based on normal data for anomaly detection and models of each type ofattack are built based on attack data for intrusion identification. Employment of PCA lowers the possibility of falsealarm generation with better detection of false alarm. It lowers the unreliability of high-interaction production honeypotby two tier surveillance system. Using short basic level unreliability can be detected while PCA hold off the experiencehacker by applying the concept of outlines