| Popis: |
Intrusion detection plays vital role in network security. Information systems which are based on computer are crucial part of any organization. In network security, detecting an intrusion is major task. Thus, the goal of intrusion detection system is to detect attack in a network domain. To check confidentiality, integrity and availability several algorithms have been implemented. These algorithms are implemented on static dataset like KDD-Cup 99, NSL-KDD, UNSW-NB 15, Kyoto 2006+ etc. But there is a challenge to impart malicious activity on real time data using machine learning algorithm. This paper provides comparative analysis of different machine learning techniques which is use to classify the data and eventually compare the performance of the techniques with respect to accuracy. Experimental results show that RF outperforms over other algorithms. |
