Design of Network Intrusion Detection based on Data Mining

• Main Authors: Meng-Shian You, 游孟修
• Other Authors: Nai-Jian Wang
• Format: Others
• Language: zh-TW
• Published: 2003
• Online Access: http://ndltd.ncl.edu.tw/handle/36712237140626366627

碩士 === 國立臺灣科技大學 === 電機工程系 === 91 === This thesis presents an approach to detect custom intrusion based on data mining framework. In this framework, custom intrusion detection is thought of as a classification. The idea is to integrate the advantage of fuzzy theory and neural networks into a new algorithm and apply this algorithm to custom intrusion detection filters. Our algorithm can extract extensive sets of features that describe each network connection, and learn rules that exactly capture the behavior of intrusion and normal activities. Finally, some examples are given to demonstrate the performance and the validity of this algorithm.