Pattern RecognitionNo Access

Intrusion Detection Based on Dynamic Gemini Population DE-K-mediods Clustering on Hadoop Platform

Wentie Wu

School of Information Engineering, Mianyang Normal University, Mianyang, P. R. China

Search for more papers by this author

and

Shengchao Xu

School of Electronic and Information Engineering, Beibu Gulf University, Qinzhou, P. R. China

E-mail Address: scxu_scholar@sina.com

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0218001421500014Cited by:5 (Source: Crossref)

Abstract

In view of the fact that the existing intrusion detection system (IDS) based on clustering algorithm cannot adapt to the large-scale growth of system logs, a K-mediods clustering intrusion detection algorithm based on differential evolution suitable for cloud computing environment is proposed. First, the differential evolution algorithm is combined with the K-mediods clustering algorithm in order to use the powerful global search capability of the differential evolution algorithm to improve the convergence efficiency of large-scale data sample clustering. Second, in order to further improve the optimization ability of clustering, a dynamic Gemini population scheme was adopted to improve the differential evolution algorithm, thereby maintaining the diversity of the population while improving the problem of being easily trapped into a local optimum. Finally, in the intrusion detection processing of big data, the optimized clustering algorithm is designed in parallel under the Hadoop Map Reduce framework. Simulation experiments were performed in the open source cloud computing framework Hadoop cluster environment. Experimental results show that the overall detection effect of the proposed algorithm is significantly better than the existing intrusion detection algorithms.

Keywords:

References

1. D. Acemoglu, A. Malekian and A. Ozdaglar, Network security and contagion, J. Economic Theo. 42(3) (2014) 38. Google Scholar
2. K. M. Carter, N. Idika and W. W. Streilein, Probabilistic threat propagation for network security, IEEE Trans. Inf. Forensics Secur. 9(9) (2014) 1394–1405. Crossref, Web of Science, Google Scholar
3. G. W. Cassales, A. S. Charão, M. Kirsch-Pinheiro et al., Improving the performance of Apache Hadoop on pervasive environments through context-aware scheduling, J. Ambient Intell. Humanized Comput. 7(3) (2016) 333–345. Crossref, Web of Science, Google Scholar
4. Z. Chen, W. Dong, H. Li et al., Collaborative network security in multi-tenant data center for cloud computing, Tsinghua Sci. Technol. 19(1) (2014) 82–94. Crossref, Web of Science, Google Scholar
5. G. Chen, Y. Gong, P. Xiao et al., Physical layer network security in the full-duplex relay system, IEEE Trans. Inf. Forensics Secur. 10(3) (2015) 574–583. Crossref, Web of Science, Google Scholar
6. Y. Chen, L. Zhang and Z. Yi, A novel low rank representation algorithm for subspace clustering, Int. J. Pattern Recog. Artific. Intell. 30(4) (2015) 1–9. Web of Science, Google Scholar
7. D. Chun-Ru, W. Y. N. Wing, W. Xi-Zhao et al., An improved differential evolution and its application to determining feature weights in similarity-based clustering, Neurocomputing 146 (2014) 95–103. Crossref, Web of Science, Google Scholar
8. P. A. Golder and K. A. Yeomans, The use of cluster analysis for stratification, Appl. Statistic. 22(2) (2018) 213–219. Crossref, Google Scholar
9. K. Kaynar, A taxonomy for attack graph generation and usage in network security, J. Inf. Secur. Appl. 29(C) (2016) 27–56. Google Scholar
10. S. H. Kim and I. Y. Lee, Block access token renewal scheme based on secret sharing in apache hadoop, Entropy 16(8) (2014) 4185–4198. Crossref, Web of Science, Google Scholar
11. M. Lee, Network security, Eng. Technol. Ref. 1(56) (2014) 495–538. Google Scholar
12. M. Liyanage, A. B. Abro, M. Ylianttila et al., Opportunities and challenges of software-defined mobile networks in network security, IEEE Secur. Privacy 14(4) (2016) 34–44. Crossref, Web of Science, Google Scholar
13. W. Luo, S. Qiao and N. Han, A k-medoids based clustering algorithm in location based social networks, J. Univ. Sci. Technol. China 47(1) (2017) 70–79. Google Scholar
14. H. Ma, X. Hao and R. Ma, Parallel PSO-kmeans algorithm based on hadoop for web log mining, Comput. Sci. s1 (2011) 479–482. Google Scholar
15. K. Siddique, Z. Akhtar, F. A. Khan et al., KDD cup 99 data sets: A perspective on the role of data sets in network intrusion detection research, Computer 52(2) (2019) 41–51. Crossref, Web of Science, Google Scholar
16. Y. X. Su and R. Chi, Multi-objective particle swarm-differential evolution algorithm, Neural Comput. Appl. 28(2) (2017) 407–418. Crossref, Web of Science, Google Scholar
17. F. Wang, Research on an automatic clustering algorithm based on improved differential evolution, Math. Practice Theo. 48(21) (2018) 187–194. Google Scholar
18. Y. Wang, Anomaly intrusion detection algorithm resistant to web attacks, Electron. Design Eng. 26(24) (2016) 132–136. Google Scholar
19. Wang, Yuping, Xiaoli et al., A space division multiobjective evolutionary algorithm based on adaptive multiple fitness functions, Int. J. Pattern Recognition Artific. Intell. 30(3) (2016) 121–128. Web of Science, Google Scholar
20. Z. J. Wang, Z. H. Zhan, Y. Lin et al., Dual-Strategy differential evolution with affinity propagation clustering for multimodal optimization problems, IEEE Trans. Evolutionary Comput. 22(6) (2018) 894–908. Crossref, Web of Science, Google Scholar
21. Wang, Zhicang, Li, et al., An evolutionary algorithm using parameter space searching for interval linear fractional bilevel programming problems, Int. J. Pattern Recog. Artific. Intell. 30(4) (2015) 54–60. Web of Science, Google Scholar
22. X.-P. Zhang, X.-Y. Zhang and J. Liu, Fuzzy kernel-clustering algorithm based on differential evolution algorithm and its application in fault diagnosis, Dianli Xitong Baohu Yu Kongzhi/Power Syst. Protect. Control 42(17) (2014) 102–106. Google Scholar