MID: An Innovative Model for Intrusion Detection by Mining Maximal Frequent Patterns
Intrusion detection is a very important topic in dependable computing. Intrusion detection system has become a vital part in network security systems with wide spread use of computer networks. It has been the recent research focus and trend to apply various kinds of data mining techniques in IDS for discovering new types of attacks efficiently,but it is still in its infancy. The most difficult part is their poor performance and accuracy. This paper presents an innovative model, called MID, that counts maximal frequent patterns for detecting intrusions, needless to count all association rules, can significantly improve the accuracy and performance of an IDS. The experimental results show that MID is efficient and accurate for the attacks that occur intensively in a short period of time.
Data mining ntrusion detection system Maximal frequent pattern Accuracy Performance
Hui Wang Chuanxiang Ma Hongjun Zhang
Wuhan Telecommunications Academy Wuhan,430010,China Computer School, Hubei University Wuhan,430070,China Information Department, 161Hospital Wuhan,430010,China
国际会议
宜昌
英文
145-148
2010-10-10（万方平台首次上网日期，不代表论文的发表时间）