作者: Jaeik Cho , Taeshik Shon , Ken Choi , Jongsub Moon
DOI: 10.1007/S11227-011-0698-X
关键词: Intrusion detection system 、 Signature (logic) 、 Dynamic learning 、 Data set 、 Pattern recognition (psychology) 、 Artificial intelligence 、 Network security 、 Machine learning 、 Computer science 、 Data mining
摘要: Machine Learning as network attack detection is one of the popular methods researched. Signature based no longer convinced efficiency in diversified intrusions (Limmer and Dressler 17th ACM Conference on Computer Communication Security, 2010). Moreover, various Zero-day attacks, non notified attacks cannot be detected (Wu Banzhaf Appl Soft Comput 10(1):1---35, This paper suggests an effective update method data set to detect attacks. In addition, this compares verifies effects Detection with updated former methods.