A Novel Immune Inspaired Concept with Neural Network for Intrusion Detection in Cybersecurity
Adeniji Oluwashola David and Ukame James Joseph. A Novel Immune Inspaired Concept with Neural Network for Intrusion Detection in Cybersecurity. International Journal of Applied Information Systems 12(30):13-17, June 2020. URL, DOI BibTeX
@article{10.5120/ijais2020451863, author = "Adeniji Oluwashola David and Ukame James Joseph", title = "A Novel Immune Inspaired Concept with Neural Network for Intrusion Detection in Cybersecurity", journal = "International Journal of Applied Information Systems", issue_date = "June 2020", volume = 12, number = 30, month = "June", year = 2020, issn = "2249-0868", pages = "13-17", url = "http://www.ijais.org/archives/volume12/number30/1087-2020451863", doi = "10.5120/ijais2020451863", publisher = "Foundation of Computer Science (FCS), NY, USA", address = "New York, USA" }
Abstract
Artificial immune system (AIS) that depicts the way the human immune system (HIS) responds to threats or attacks in the body . AIS was used by researchers to solve intrusion problems.Immune system algorithms like the clonal selection theory, immune networks, negative selection algorithms and danger theory concepts, although has achieved some level of results, but not adequate especially in the cybersecurity domain. In this study a model based on AIS concepts that will find a significant application in cybersecurity was developed.The negative selection algorithm (NSA) which is a class of very flexible algorithm will divide the problem space into self and non-self which was used to build the model. The detector generation phase of the NSA was improved and a neural network technique was incorporated to build the model. The developed model called NNET NSA (Neural Network Negative Selection Algorithm) used the NSLKDDCup1999 dataset to test the model. An R script was written using the R programming language and implementation was done on both Rstudio and Rapid Miner environments.Experimental results showed that the model NNET NSA achieved a high classification accuracy of 90.1% within a computation time of 15seconds as compared with two classification algorithms; support vector machine (SVM) and Naïve Bayes which achieved a classification accuracy of 65.01% and 81.66% within a computation time of both 215.81seconds and 100.15seconds respectively on the R console. The developed model (NNET NSA) further showed a low wrong classification of 3.9% as compared with SVM; 4.8% and Naive Bayes; 4.2% respectively.
Reference
- Julie Greensmith, Amanda Whitbrook, U. A. (2010). Artificial Immune Systems. nternational Series in Operations Research & Management Science, 146, 421–448, Springer Dordrecht.
- Aickelin, U, Bentley, P., Cayzer, S.,Kim, J., & Mcleod, J. (2003). Danger Theory?: The Link between AIS and IDS??, 147–155.
- Prakash, A., & Deshmukh, S. G.(2011). A multi-criteria customer allocation problem in supply chain environment?: An artificial immune system with fuzzy logic controller based approach. Expert Systems With Applications, 38(4), 3199–3208. https://doi.org/10.1016/j.eswa.2010.09. 008.
- Dutt, I., Borah, S., & Maitra, I. (2016). Intrusion Detection System using Artificial Immune System. International Journal of Computer Applications, 44(12), 19–22.
- Lunt, B. M., & Ekstrom, J. J. (2008).The IT model curriculum. Proceedings of the 9th ACM SIGITE Conference on Information Technology Education - SIGITE ’08,
- Ye, G., Wang, Y., & Sun, Q. (2019).Super Base Station Fault Detection Mechanism Based on Negative Selection Algorithm and Expert Knowledge Base. IOP Conference Series:Materials Science and Engineering, 490(07), 1-6 IOP publishing.
- Adeniji O.d., Olatunji O.O (2020). Zero Day Attack Prediction with Parameter Setting Using Bi Direction Recurrent Neural Network in Cyber Security.International Journal of Computer Science and Information Security (IJCSIS), Vol. 18, No. 3,pp 111-118
- S.D Adeniji, S Khatun, RSA Raja, MA Borhan (2008).‘Design and analysis of resource management support software for multihoming in vehicle of IPv6 Network. Proceedings of the Fifth IASTED International Conference.Vol 607,issue 089.pp 13.
- Olushola D Adeniji, Olubukola Adigun, Omowumi O Adeyemo (2013) An intelligent spam-scammer filter mechanism using bayesian techniquesInternational Journal of Computer Science and Information Security (IJCSIS), Vol. 10, No. 3 pp 126
- S.D Adeniji, S Khatun, MA Borhan, RSA Raja, (2008) A design proposer on policy framework in IPV6 network.2008 IEEE International Symposium on Information Technology.Vol 4,pp 1-6
- Logunleko K.B., Adeniji. O.D., Logunleko A.M, (2020). A Comparative Study of Symmetric Cryptography Mechanism on DES, AES and EB64 for Information Security. International Journal of Scientific Research in Computer Science and Engineering Vol.8, Issue.1, pp.45-51.
- Revathi, S., & Malathi, A. (2013). ADetailed Analysis on NSL-KDD Dataset Using Various Machine Learning Techniques for Intrusion Detection. International Journal of Engineering Research and Technology (IJERT), 2(12), 1848–1853.
- Thabiso Peter Mpofu, D. G. V. R. R.(2014). Artificial Immune Systems: A Predictive Model for credit scoring.International Journal of Scientific Engineering Research, 5(8), 1–5.
- Chen, Y., Abraham, A., & Grosan, C. (2018). Cyber Security And The Evolution Of Intrusion Detection Systems. I-Manager’s Journal on Future Engineering and Technology, 1(1), 74–82.
- Cui, L., Pi, D., & Chen, C. (2015).BIORV-NSA?: Bidirectional inhibition optimization r-variable negative selection algorithm and its application. Applied Soft Computing Journal, 32,544–552.
Keywords
Artificial Immune System, Artificial Neural Network, Cybersecurity, intrusion detection