Open Access Open Access  Restricted Access Subscription Access

Distributed and Cooperative Multi-agent Based Intrusion Detection System


Affiliations
1 Department of CSE, Jeppiaar Engineering College, Tamil Nadu–600119, India
2 Department of CSE, RMK Engineering College, Tamil Nadu–601 206
 

One of the primary challenges in intrusion detection is modeling typical application behavior, so that we can recognize attacks by their atypical effects without raising too many false alarms. IDS implemented using mobile agents is one of the new paradigms for intrusion detection. In this paper, we have proposed an effective intrusion detection system in which local agent collects data from its own system and it classifies anomaly behaviors using SVM classifier. Each local agent is capable of removing the host system from the network on successful detection of attacks. The mobile agent gathers information from the local agent before it allows the system to send data. Our system identifies successful attacks from the anomaly behaviors. Experimental results show that the proposed system has high detection rate and low false alarm rate which encourages the proposed system.

Keywords

Mobile Agents, Classification, Intrusion Detection System, Packet Loss, Network Security
User

  • Bhuse V and Gupta A (2006) Anomaly intrusion detection in wireless sensor networks.J. High Speed Networks. 15(1), 33–51.
  • Bo Sun, Wu K, Xiao Y and Wang R (2006) Integration of mobility and intrusion detection for wireless ad hoc networks DOI: 10.1002/dac.853.
  • Bradley KA, Cheung S, Puketza N, Mukherjee B and Olsson RA (1998) Detecting disruptive routers: A distributed network monitoring approach. Proc. IEEE Symp. Security Privacy. pp:115-124.
  • Cabrera D and Gutiérrez C and Raman K. Mehra (2008) Ensemble methods for anomaly detection and distributed intrusion detection in mobile Ad-Hoc networks.Elsevier Sci. Publishers. 9(1), 96-119.
  • Chen H, Han P, Zhou X and Gao C (2007) Lightweight anomaly intrusion detection in wireless sensor networks. Intelligence Security Informatics. Springerlink.
  • Deng H, Xu, R, Li, J, Zhang, F, Levy, R and Lee W (2008) Agent-based cooperative anomaly detection for wireless ad hoc networks. Parallel Distributed Sys. 1, 8.
  • Liu Y, Comaniciu C and Man H (2006) A Bayesian game approach personal wireless communications. ACM 159593507X.
  • Liu Y, Li Y and Man H (2005) MAC layer anomaly detection in Ad Hoc networks. Proc. of the 6th IEEE Information Assurance Workshop. pp: 402-409.
  • Mishra A and Nadkarni K (2003) Security in wireless Ad Hoc networks. CRC press LLC.
  • Mishra A, Nadkarni K and Animesh Patcha (2004) Intrusion detection in wireless Ad Hoc networks. IEEE Wireless Commun. pp: 48-60.
  • Mizrak AT, Cheng YC, Marzullo K and Savage S (2006) Detecting and isolating malicious routers. IEEE Trans. Dependable Secure Computing. 3(3), 230-244.
  • Perlman R (1988) Network layer protocols with byzantine robustness, MIT LCS TR-429.
  • Puttini R, Hanashiro M, García-Villalba J and Barenco CJ (2006) On the anomaly intrusion-detection in mobile Ad Hoc network environments. Personal Wireless Commun. Vol. 4217/2006, Springerlink.
  • Subhadrabandhu FAD and Sarkar S (2008) Signature based intrusion detection for wireless Ad-Hoc networks: A comparative study of various routing protocols. Seas.
  • Y.G. Liu, K.F. Chen, X.F. Liao, and W.Zhang (2004) A genetic clustering method for intrusion detection. Pattern Recognition, 37(5), 927-942.
  • S.T. Sarasamma, Q.A. Zhu and J. Huff (2005) Hierarchial kohonenen net for anomaly detection in network security. IEEE Transactions on Systems, Man & Cybernetics. 32(2), 302-312.

Abstract Views: 431

PDF Views: 121




  • Distributed and Cooperative Multi-agent Based Intrusion Detection System

Abstract Views: 431  |  PDF Views: 121

Authors

J. Arokia Renjit
Department of CSE, Jeppiaar Engineering College, Tamil Nadu–600119, India
K. L. Shunmuganathan
Department of CSE, RMK Engineering College, Tamil Nadu–601 206

Abstract


One of the primary challenges in intrusion detection is modeling typical application behavior, so that we can recognize attacks by their atypical effects without raising too many false alarms. IDS implemented using mobile agents is one of the new paradigms for intrusion detection. In this paper, we have proposed an effective intrusion detection system in which local agent collects data from its own system and it classifies anomaly behaviors using SVM classifier. Each local agent is capable of removing the host system from the network on successful detection of attacks. The mobile agent gathers information from the local agent before it allows the system to send data. Our system identifies successful attacks from the anomaly behaviors. Experimental results show that the proposed system has high detection rate and low false alarm rate which encourages the proposed system.

Keywords


Mobile Agents, Classification, Intrusion Detection System, Packet Loss, Network Security

References





DOI: https://doi.org/10.17485/ijst%2F2010%2Fv3i10%2F29834