Artificial immune theory based network intrusion detection system and the algorithms design

A network intrusion detection model based on artificial immune theory is proposed in this paper. In this model, self patterns and non-self patterns are built upon frequent behaviors sequences, then a simple but efficient algorithm for encoding patterns is proposed. Based on the result of encoding, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiang-Rong Yang, Jun-Yi Shen, Rui Wang
Format: Conference Proceeding
Language:English
Subjects:
Algorithm design and analysis
Biology computing
Computer science
Computer security
Condition monitoring
Detectors
Encoding
Humans
Immune system
Intrusion detection
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A network intrusion detection model based on artificial immune theory is proposed in this paper. In this model, self patterns and non-self patterns are built upon frequent behaviors sequences, then a simple but efficient algorithm for encoding patterns is proposed. Based on the result of encoding, another algorithm for creating detectors is presented, which integrates a negative selection with the clonal selection. The algorithm performance is analyzed, which shows that this method can shrink each generation scale greatly and create a good niche for patterns evolving.
DOI:10.1109/ICMLC.2002.1176712