Architecture for an Artificial Immune System

被引：506

作者：

Hofmeyr, Steven A. ^{[1
]}

Forrest, Stephanie ^{[1
]}

机构：

[1] Santa Fe Inst, Santa Fe, NM 87501 USA

来源：

EVOLUTIONARY COMPUTATION | 2000年 / 8卷 / 04期

基金：

美国国家科学基金会;

关键词：

Immune system; distributed; adaptive; classifier systems; anomaly detection; network intrusion detection;

D O I：

10.1162/106365600568257

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An artificial immune system (ARTIS) is described which incorporates many properties of natural immune systems, including diversity, distributed computation, error tolerance, dynamic learning and adaptation, and self-monitoring. ARTIS is a general framework for a distributed adaptive system and could, in principle, be applied to many domains. In this paper, ARTIS is applied to computer security in the form of a network intrusion detection system called LISYS. LISYS is described and shown to be effective at detecting intrusions, while maintaining low false positive rates. Finally, similarities and differences between ARTIS and Holland's classifier systems are discussed.

引用

页码：443 / 473

页数：31

共 42 条

[1] Albitz P., 1992, DNS BIND
[2] [Anonymous], 1999, NETRANGER
[3] [Anonymous], 2001, The Immune System in Health and Disease
[4] ASIM, 1996, B266140 ASIM GAO
[5] Brooks R. A., 1989, Journal of the British Interplanetary Society, V42, P478
[6] CACM, 1999, COMMUNICATIONS ASS C
[7] The brain has a body: adaptive behavior emerges from interactions of nervous system, body and environment
Chiel, HJ
Beer, RD
[J]. TRENDS IN NEUROSCIENCES, 1997, 20 (12) : 553 - 557
[8] Crosbie M., 1994, DEFENDING COMPUTER S
[9] Dasgupta D, 1999, GECCO-99: PROCEEDINGS OF THE GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, P149
[10] An immunological approach to change detection: Theoretical results
Dhaeseleer, P
[J]. 9TH IEEE COMPUTER SECURITY FOUNDATIONS WORKSHOP, PROCEEDINGS, 1996, : 18 - 26

← 1 2 3 4 5 →