Uticaj preprocesuiranja na detekciju napada zasnovanih na anomalijama

  • Danijela Protić Vojska Srbije, Generalštab, Uprava za telekomunikacije i informatiku (J-6), Centar za primenjenu matematiku i elektroniku, Beograd, Republika Srbija https://orcid.org/0000-0003-0827-2863
Ključne reči: detekcija anomalija, mašinsko učenje, Kyoto 2006

Sažetak


Uvod/cilj: Sistem za detekciju upada koji se zasniva na detekciji anomalije otkriva napad na računarsku mrežu na osnovu referentnog modela koji identifikuje normalno ponašanje računarske mreže i detektuje anomaliju. Modeli mašinskog učenja klasifikuju upade ili zloupotrebe u dve grupe: grupu normalnog saobraćaja i grupu anomalija. U složenim računarskim mrežama broj instanci u obučavajućem skupu može biti veliki, što evaluaciju modela klasifikatora čini teškom.

Metode: U radu je prikazan algoritam za izbor atributa koji smanjuje veličinu skupa podataka.

Rezultati: Eksperimenti su izvedeni na skupu podataka iz Kyoto 2006+ baze i na četiri modela klasifikatora: modelu feedforward neuronska mreža, modelu k-najbližih suseda, modelu ponderisanih k-najbližih suseda i modelu stabla odlučivanja. Rezultati pokazuju visoku tačnost modela.

Zaključak: Preprocesuiranje trokoračnim algoritmom za izbor atributa i normalizaciju instanci rezultiralo je poboljšanjem performansi četiri binarna klasifikatora i smanjilo vreme procesuiranja.

Reference

Ambedkar C. & Kishore Babu, V.2015. Detection of Probe Attacks Using Machine Learning Techniques. International Journal of Research Studies in Computer Science and Engineering, 2(3), pp.25-29 [online]. Available at: https://www.arcjournals.org/pdfs/ijrscse/v2-i3/7.pdf [Accessed: 29 June 2020].

Ashok Kumar, D. & Venugopalan, S.R. 2018.A Novel algorithm for Network Anomaly Detection using Adaptive Machine Learning. Singapore: Springer Singapore.

Kwak, Y.T., Hwang, J.W., & Yoo, C.J. 2011. A new damping strategy of Levenberg-Marquardt algorithm for multilayer perceptrons. Neural Network World, 21(4), pp.327-340. Available at: https://doi.org/10.14311/NNW.2011.21.020.

Levenberg, K. 1944. A method for the solution of certain problems in least squares. Quarterly of Applied Mathematics, 2, pp.164-168 Available at: https://doi.org/10.1090/qam/10666.

Marquardt, D.W. 1963. An Algorithm for Least-Squares Estimation of Nonlinear Parameters. Journal of the Society for Industrial and Applied Mathematics, 11(2), pp.431-441 [online]. Available at: https://www.jstor.org/stable/2098941?seq=1 [Accessed: 29 June 2020].

Nguyen, T.T.T. & Armitage, G. 2008. A Survey of Techniques for Internet Traffic Classification using Machine Learning. IEEE Communications Surveys & Tutorials, 10(4), pp.56-76. Available at: https://doi.org/10.1109/SURV.2008.080406.

Protić, D.D. 2018. Review of KDD CUP ’99, NSL-KDD and KYOTO 2006+ Datasets. Vojnotehnički glasnik/Military Technical Courier, 66(3), pp.580-596. Available at: https://doi.org/10.5937/vojtehg66-16670.

Protić, D. & Stanković, M. 2018. Anomaly-Based Intrusion Detection: Feature Selection and Normalization Influence to the Machine Learning Models Accuracy. European Journal of Formal Sciences and Engineering, 2(3), pp.101-106. Available at: http://dx.doi.org/10.26417/ejef.v2i3.p101-106.

Protić, D. & Stanković, M. 2020. Detection of Anomalies in the Computer Network Behavior. European Journal of Formal Sciences and Engineering, 4(1), pp.7-13. Available at: http://dx.doi.org/10.26417/ejef.v4i1.p7-13.

Song, J., Takakura, H., Okabe, Y., Eto, M., Inoue, D. & Nakao, K. 2011. Statistical Analysis of Honeypot Data and Building of Kyoto 2006+ Dataset forNIDS Evaluation. In: Proc. 1st Work-shop on BADGES - Building Anal. Datasets and Gathering Experience Returns for Security, Salzburg, pp.29-36, April 10-13. Available at: https://doi.org/10.1145/1978672.1978676.

-Split. 2020. What is false positive rate? [online]. Available at: https://www.split.io/glossary/false-positive-rate/ [Accessed: 29 June 2020].

Shirabad, J.S., Lethbridge, T.C. & Matwin, S. 2007. Modeling Relevance Relations Using Machine Learning Techniques. In: Zhang, D. & Tsai, J.J.P. (Eds.) Advances in Machine Learning Applications in Software Engineering, Chapter VIII, pp.168-207. Hershey, PA: Idea Group Pub. (IGI Global research collection). Available at: https://doi.org/10.4018/978-1-59140-941-1.ch008.

-Takakura. 2020. Traffic Data from Kyoto University’s Honeypots [online]. Available at: http://www.takakura.com/kyoto_data/ [Accessed: 29.06.2020].

Tsigkritis, T., Groumas G. & Schneider M. 2018. On the Use of k-NN in Anomaly Detection. Journal of Information Security, 9(1), pp.70-84. Available at: https://doi.org/10.4236/jis.2018.91006.

Objavljeno
2020/06/01
Rubrika
Originalni naučni radovi