A hybrid intrusion detection system based on different machine learning algorithms

• Main Authors: Atefi, Kayvan, Yahya, Saadiah, Dak, Ahmad Yusri, Atefi, Arash
• Format: Conference or Workshop Item
• Language: English
• Published: 2013
• Subjects: QA76 Computer software
• Online Access: http://repo.uum.edu.my/12031/1/PID22.pdf; http://repo.uum.edu.my/12031/; http://www.icoci.cms.net.my/proceedings/2013/TOC.html

Recently, Networks have developed quickly during the last many years, and attacks on network infrastructure presently are main threats against network and information security.With quickly growing unauthorized activities in network Intrusion Detection as a part of defense is extremely necessary because traditional firewall techniques cannot provide complete protection against intrusion. There are numerous study in intrusion detection system (IDS) especially with Genetic algorithms (GA) and Support Vector Machine (SVM) but most of them did not get the potential of hybrid SVM using GA. Hence this study aims to hybrid GA and forbids with high accuracy.The paper illustrates the benefit of hybrid SVM via GA also the paper has proven that by enhancing SVM with GA can reduce false alarms and mean square error (MSE) in detecting intrusion.