|Table of Contents|

Artificial Immunity-based Misbehavior Detection Architecture for Mobile Ad Hoc Networks


Research Field:
Publishing date:


Artificial Immunity-based Misbehavior Detection Architecture for Mobile Ad Hoc Networks
LIAO Jun12 LIU Yao-zong1 JIANG Hai-tao1ZHANG Hong1
1. School of Computer Science and Technology,NUST,Nanjing 210094,China; 2. Department of Information Management and Information Systems,China Pharmaceutical University,Nanjing 210009,China
mobile ad hoc networks artificial immunity misbehavior detection clustering
To meet the security requirements and the hierarchical characteristics of ad hoc networks, an artificial immunity-based misbehavior detection system( AIMDS) architecture is proposed here. The misbehavior detection datasets of the AIMDS architecture are classified into intra-cluster nodes subsets and cluster-head nodes subsets, and they are performed by binary encoding and numeric encoding respectively. With the intra-cluster node detector match behavior and the cluster-head nodes cooperation,a layered-dynamic detection algorithm of antigens( misbehaviors) is applied to verify the node misbehavior. The simulation results show that,when the misbehavior node rate is 0 ~ 40%, the detection rate and the false-positive rate of the proposed architecture are higher than 87. 6% and lower than 1. 01% respectively, and its performance is better than the DSR-Probe algorithm.


[1] Marti Sergio,Giuli T J,Lai Kevin, et al. Mitigating routing misbehavior in mobile ad hoc networks[A]. Proc of the ACM MobiCom[C]. New York,USA: ACM Press, 2000: 255-265.
[2] Buchegger Sonja,Le Boudec Jean-Yves. Performance analysis of the CONFIDANT protocol: Cooperation of nodes: Fairness in distributed ad hoc networks[A]. Proc IEEE/ACM Symp Mobile Ad hoc Networking and Computing( MobiHOC) [C]. IEEE, 2002: 80-91.
[3] Michiardi P,Molva R. Core: A collaborative reputation mechanism to enforce node cooperation in mobile ad hoc networks[A]. Proc of the Communications and Multimedia Security[C]. Portoroz: IFIP Press,2002: 376-386.
[4] Forrest S,Beauchemin C. Computer immunology[J]. Immunological Reviews, 2007, 216( 1) : 176-197.
[5] Dasgupta D,Gonzalez F. CIDS: An agent-based intrusion detection system[J]. Computers and Security,2005,24 ( 5) : 387-398.
[6] Kim Jungwon,Bentley P,Aickelin Uwe,et al. Immune system approaches to detection—a review intrusion [J]. Natural Computing, 2007,6 ( 4) : 413-466.
[7] Sarafijanovic Slavisa,Le Boudec Jean-Yves. An artificial immune system approach with secondary response for misbehavior detection in mobile ad hoc networks[J]. IEEE Transaction on Neural Networks,2005,16 ( 5) : 1076-1087.
[8] William S H. An artificial immune system for securing mobile ad hoc networks against intrusion attacks[A]. Proc of SPIE[C]. Bellingham,USA: SPIE Press, 2003: 74-91.
[9] Hofmery S,Forrest S. Architecture for an artificial immune system [J]. Evolutionary Computation,2000, 7( 1) : 45-68.
[10] 潘志松,倪桂强,谭琳,等. 异常检测中单类分类算 法和免疫框架设计[J]. 南京理工大学学报,2006, 30( 1) : 48-52.
[11] Copt Samuel,Victoria-Feser Maria-Pia. Fast algorithms for computing high breakdown covariance matrices with missing data[A]. Theory and Applications of Recent Robust Methods[C]. Basel,Switzerland: Birkhauser Verlag, 2004: 71-82.
[12] Just M,Kranakis E,Wan T. Resisting malicious packet dropping in wireless ad hoc networks[A]. Proc of ADHOCNOW’ 03[C]. Montreal,Canada: Springer,2003: 151-163.


Last Update: 2012-10-24