An Immuno Control Framework for Decentralized Mechatronic Control

Wing Yin Albert KO, H.Y.K. LAU, T. L. LAU

Research output: Journal PublicationsJournal Article (refereed)Researchpeer-review

Abstract

Nodes that build a mobile ad-hoc network participate in a common routing protocol in order to provide multi-hop radio communication. Routing defines how control information is exchanged between nodes in order to find the paths between communication pairs, and how data packets are relayed. Such networks are vulnerable to routing misbehavior, due to faulty, selfish or malicious nodes. Misbehavior disrupts communication, or even makes it impossible in some cases. Misbehavior detection systems aim at removing this vulnerability. For this purpose, we use an Artificial Immune System (AIS) approach, i.e, an approach inspired by the human immune system (HIS). Our goal is to make an AIS that, analogously to its natural counterpart [16], automatically learns and detects new misbehavior, but becomes tolerant to previously unseen normal behavior. We achieve this goal by adding some new AIS concepts to those that already exist: (1) the virtual thymus, which provides a dynamic description of normal behavior in the system; (2) “clustering” is a decision making method that reduces the false-positive detection probability and minimizes the time until detection; (3) we apply the “danger signal” approach, that is recently proposed in AIS literature [5,6] as a way to obtain feedback from the protected system and use it for correct learning and final decisions making; (4) we use “memory detectors”, a standard AIS solution to achieve fast secondary response. We implement our AIS in a network simulator and test it on two types of misbehavior. Performance analysis shows the following effects on the detection capabilities: (1) the virtual thymus enables the system to: (a) learn and detect misbehavior without use of the preliminary misbehavior is-absent training phase, and (b) have low false positive detections even if normal behavior changes over time; (2) clustering and danger signal are useful for achieving low false positives; (3) memory detectors significantly accelerate the secondary response of the system.
Original languageEnglish
Pages (from-to)255-280
Number of pages26
JournalInternational Journal of Unconventional Computing
Volume1
Issue number3
Publication statusPublished - 2005
Externally publishedYes

Fingerprint

Immune system
Mechatronics
Thymus
Decision making
Detectors
Data storage equipment
Radio communication
Communication
Mobile ad hoc networks
Routing protocols
Simulators
Feedback

Cite this

@article{3b5a5c83d4a24207a60cf21f0815f25b,
title = "An Immuno Control Framework for Decentralized Mechatronic Control",
abstract = "Nodes that build a mobile ad-hoc network participate in a common routing protocol in order to provide multi-hop radio communication. Routing defines how control information is exchanged between nodes in order to find the paths between communication pairs, and how data packets are relayed. Such networks are vulnerable to routing misbehavior, due to faulty, selfish or malicious nodes. Misbehavior disrupts communication, or even makes it impossible in some cases. Misbehavior detection systems aim at removing this vulnerability. For this purpose, we use an Artificial Immune System (AIS) approach, i.e, an approach inspired by the human immune system (HIS). Our goal is to make an AIS that, analogously to its natural counterpart [16], automatically learns and detects new misbehavior, but becomes tolerant to previously unseen normal behavior. We achieve this goal by adding some new AIS concepts to those that already exist: (1) the virtual thymus, which provides a dynamic description of normal behavior in the system; (2) “clustering” is a decision making method that reduces the false-positive detection probability and minimizes the time until detection; (3) we apply the “danger signal” approach, that is recently proposed in AIS literature [5,6] as a way to obtain feedback from the protected system and use it for correct learning and final decisions making; (4) we use “memory detectors”, a standard AIS solution to achieve fast secondary response. We implement our AIS in a network simulator and test it on two types of misbehavior. Performance analysis shows the following effects on the detection capabilities: (1) the virtual thymus enables the system to: (a) learn and detect misbehavior without use of the preliminary misbehavior is-absent training phase, and (b) have low false positive detections even if normal behavior changes over time; (2) clustering and danger signal are useful for achieving low false positives; (3) memory detectors significantly accelerate the secondary response of the system.",
author = "KO, {Wing Yin Albert} and H.Y.K. LAU and LAU, {T. L.}",
year = "2005",
language = "English",
volume = "1",
pages = "255--280",
journal = "International Journal of Unconventional Computing",
issn = "1548-7199",
publisher = "Old City Publishing",
number = "3",

}

An Immuno Control Framework for Decentralized Mechatronic Control. / KO, Wing Yin Albert; LAU, H.Y.K.; LAU, T. L.

In: International Journal of Unconventional Computing, Vol. 1, No. 3, 2005, p. 255-280.

Research output: Journal PublicationsJournal Article (refereed)Researchpeer-review

TY - JOUR

T1 - An Immuno Control Framework for Decentralized Mechatronic Control

AU - KO, Wing Yin Albert

AU - LAU, H.Y.K.

AU - LAU, T. L.

PY - 2005

Y1 - 2005

N2 - Nodes that build a mobile ad-hoc network participate in a common routing protocol in order to provide multi-hop radio communication. Routing defines how control information is exchanged between nodes in order to find the paths between communication pairs, and how data packets are relayed. Such networks are vulnerable to routing misbehavior, due to faulty, selfish or malicious nodes. Misbehavior disrupts communication, or even makes it impossible in some cases. Misbehavior detection systems aim at removing this vulnerability. For this purpose, we use an Artificial Immune System (AIS) approach, i.e, an approach inspired by the human immune system (HIS). Our goal is to make an AIS that, analogously to its natural counterpart [16], automatically learns and detects new misbehavior, but becomes tolerant to previously unseen normal behavior. We achieve this goal by adding some new AIS concepts to those that already exist: (1) the virtual thymus, which provides a dynamic description of normal behavior in the system; (2) “clustering” is a decision making method that reduces the false-positive detection probability and minimizes the time until detection; (3) we apply the “danger signal” approach, that is recently proposed in AIS literature [5,6] as a way to obtain feedback from the protected system and use it for correct learning and final decisions making; (4) we use “memory detectors”, a standard AIS solution to achieve fast secondary response. We implement our AIS in a network simulator and test it on two types of misbehavior. Performance analysis shows the following effects on the detection capabilities: (1) the virtual thymus enables the system to: (a) learn and detect misbehavior without use of the preliminary misbehavior is-absent training phase, and (b) have low false positive detections even if normal behavior changes over time; (2) clustering and danger signal are useful for achieving low false positives; (3) memory detectors significantly accelerate the secondary response of the system.

AB - Nodes that build a mobile ad-hoc network participate in a common routing protocol in order to provide multi-hop radio communication. Routing defines how control information is exchanged between nodes in order to find the paths between communication pairs, and how data packets are relayed. Such networks are vulnerable to routing misbehavior, due to faulty, selfish or malicious nodes. Misbehavior disrupts communication, or even makes it impossible in some cases. Misbehavior detection systems aim at removing this vulnerability. For this purpose, we use an Artificial Immune System (AIS) approach, i.e, an approach inspired by the human immune system (HIS). Our goal is to make an AIS that, analogously to its natural counterpart [16], automatically learns and detects new misbehavior, but becomes tolerant to previously unseen normal behavior. We achieve this goal by adding some new AIS concepts to those that already exist: (1) the virtual thymus, which provides a dynamic description of normal behavior in the system; (2) “clustering” is a decision making method that reduces the false-positive detection probability and minimizes the time until detection; (3) we apply the “danger signal” approach, that is recently proposed in AIS literature [5,6] as a way to obtain feedback from the protected system and use it for correct learning and final decisions making; (4) we use “memory detectors”, a standard AIS solution to achieve fast secondary response. We implement our AIS in a network simulator and test it on two types of misbehavior. Performance analysis shows the following effects on the detection capabilities: (1) the virtual thymus enables the system to: (a) learn and detect misbehavior without use of the preliminary misbehavior is-absent training phase, and (b) have low false positive detections even if normal behavior changes over time; (2) clustering and danger signal are useful for achieving low false positives; (3) memory detectors significantly accelerate the secondary response of the system.

M3 - Journal Article (refereed)

VL - 1

SP - 255

EP - 280

JO - International Journal of Unconventional Computing

JF - International Journal of Unconventional Computing

SN - 1548-7199

IS - 3

ER -