ntvНаучно-технический вестник информационных технологий, механики и оптикиScientific and Technical Journal of Information Technologies, Mechanics and Optics2226-14942500-0373Университет ИТМО10.17586/2226-1494-2022-22-1-93-100ntv-276Research ArticleКОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИCOMPUTER SCIENCEСнижение размерности атрибутов с использованием нечетко оптимизированного независимого компонентного анализа для системы обнаружения вторжений в большие данныеDimensionality reduction of the attributes using fuzzy optimized independent component analysis for a Big Data Intrusion Detection Systemhttps://orcid.org/0000-0002-6968-4653АсуанандиниР.AswanandiniR.

Асуанандини Раджан — PhD, доцент; докторант

sc 57211403371

Коимбатур, 641035

Коимбатур, 641006

Rajan Aswanandini — PhD, Assistant Professor; PhD Student

sc 57211403371

Coimbatore, 641035

Coimbatore, 641006

aswanandini1981@gmail.comhttps://orcid.org/0000-0002-1681-9059ДипаЧ.DeepaCh.

Дипа Чандран — PhD, доцент

sc 56218174800

Коимбатур, 641006

Chandran Deepa — PhD, Associate Professor

sc 56218174800

Coimbatore, 641006

deepapkd@gmail.comКГ Колледж искусств и науки; Колледж искусств и наук Шри РамакришныИндияKG College of Arts and Science; Sri Ramakrishna College of Arts and ScienceIndiaКолледж искусств и наук Шри РамакришныИндияSri Ramakrishna College of Arts and ScienceIndia20221712202422193100Copyright © Асуанандини Р., Дипа Ч., 20242024Асуанандини Р., Дипа Ч.Aswanandini R., Deepa C.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://ntv.elpub.ru/jour/article/view/276

Исследования кибербезопасности больших данных в последние годы стали привлекать большое внимание благодаря разработке передовых классификаторов машинного и глубокого обучения. Новые алгоритмы классификаторов значительно улучшили системы обнаружения вторжений. На производительность классификаторов положительно влияют наиболее релевантные функции, в то время как наличие менее релевантных функций отрицательно влияет на их производительность. Учет всех атрибутов, особенно атрибутов высокой размерности, увеличивает вычислительную сложность. По этой причине, важно уменьшить размерность атрибутов для повышения производительности классификатора. Для достижения этой цели представлен эффективный подход к снижению размерности атрибутов посредством разработки метода нечеткого оптимизированного анализа независимых компонентов (Fuzzy Optimized Independent Component Analysis, FOICA). Стандартный независимый компонентный анализ (Independent Component Analysis, ICA) сочетается с нечеткой энтропией для преобразования атрибутов высокой размерности в атрибуты низкой размерности и помогает в выборе высокоинформативных атрибутов низкой размерности. Выбранные функции передаются в эффективные гибридные классификаторы, а именно в гиперэвристические машины опорных векторов (Hyper[1]heuristic Support Vector Machines, HH-SVM), гиперэвристические машины опорных векторов с улучшенной оптимизацией роя частиц (Hyper-Heuristic Improved Particle Swarm Optimization based Support Vector Machines, HHIPSO-SVM) и сверточные нейронные сети на основе гиперэвристического алгоритма светлячков (Hyper[1]Heuristic Firefly Algorithm based Convolutional Neural Networks, HHFA-CNN) для классификации данных кибербезопасности и выявления вторжений. Проведены эксперименты с использованием двух наборов данных о кибербезопасности и лабораторных данных в реальном времени. Полученные результаты подтвердили превосходство предложенной модели Intrusion Detection Systems на основе уменьшения размерности FOICA.

Big data cybersecurity has garnered more attraction in recent years with the development of advanced machine learning and deep learning classifiers. These new classifier algorithms have significantly improved Intrusion Detection Systems (IDS). In these classifiers, the performance is positively influenced by high relevant features while less relevant features negatively influence the performance. However, considering all the attributes, especially the high dimensional attributes, increases computational complications. Hence it is essential to diminish the dimensionality of the attributes to improve the classifier performance. To achieve this objective, an efficient dimensionality reduction approach is presented through the development of the Fuzzy Optimized Independent Component Analysis (FOICA) technique. The standard Independent Component Analysis (ICA) is coupled with the fuzzy entropy to transform the high dimension attributes into low dimension attributes and helps in selecting high informative low-dimensional attributes. These selected features are fed to efficient hybrid classifiers namely Hyper-heuristic Support Vector Machines (HH-SVM), Hyper-Heuristic Improved Particle Swarm Optimization based Support Vector Machines (HHIPSO-SVM) and Hyper-Heuristic Firefly Algorithm based Convolutional Neural Networks (HHFA-CNN) to classify the cybersecurity data to identify the intrusions. Experiments are conducted over two cybersecurity datasets and real-time laboratory data whose outcomes specify the supremacy of the suggested IDS model based on FOICA dimensionality reduction.

большие данные о вторженияхкибербезопасностьсистема обнаружения вторженийнезависимый компонентный анализуменьшение размерностигиперэвристический алгоритм светлячкасверточные нейронные сетиNSL-KDDbig intrusion datacybersecurityintrusion detection systemindependent component analysisdimensionality reductionhyper-heuristic firefly algorithmconvolutional neural networksNSL-KDDReferencesLiao H.J., Lin C.H.R., Lin Y.C., Tung K.Y. Intrusion detection system: A comprehensive review // Journal of Network and Computer Applications. 2013. V. 36. N 1. P. 16–24. https://doi.org/10.1016/j.jnca.2012.09.004Liao H.J., Lin C.H.R., Lin Y.C., Tung K.Y. Intrusion detection system: A comprehensive review // Journal of Network and Computer Applications. 2013. V. 36. N 1. P. 16–24. https://doi.org/10.1016/j.jnca.2012.09.004Ashoor A.S., Gore S. Importance of intrusion detection system (IDS) // International Journal of Scientific and Engineering Research. 2011. V. 2. N 1. P. 1–4.Ashoor A.S., Gore S. Importance of intrusion detection system (IDS) // International Journal of Scientific and Engineering Research. 2011. V. 2. N 1. P. 1–4.Wang Q., Lu P. Research on application of artificial intelligence in computer network technology // International Journal of Pattern Recognition and Artificial Intelligence. 2019. V. 33. N 5. P. 1959015. https://doi.org/10.1142/S0218001419590158Wang Q., Lu P. Research on application of artificial intelligence in computer network technology // International Journal of Pattern Recognition and Artificial Intelligence. 2019. V. 33. N 5. P. 1959015. https://doi.org/10.1142/S0218001419590158Chen T.M., Walsh P.J. Guarding against network intrusions // Computer and Information Security Handbook. 2013. P. 81–95. https://doi.org/10.1016/B978-0-12-394397-2.00005-2Chen T.M., Walsh P.J. Guarding against network intrusions // Computer and Information Security Handbook. 2013. P. 81–95. https://doi.org/10.1016/B978-0-12-394397-2.00005-2Khraisat A., Gondal I., Vamplew P., Kamruzzaman J. Survey of intrusion detection systems: techniques, datasets and challenges // Cybersecurity. 2019. V. 2. N 1. P. 20. https://doi.org/10.1186/s42400-019-0038-7Khraisat A., Gondal I., Vamplew P., Kamruzzaman J. Survey of intrusion detection systems: techniques, datasets and challenges // Cybersecurity. 2019. V. 2. N 1. P. 20. https://doi.org/10.1186/s42400-019-0038-7Liu H., Lang B. Machine learning and deep learning methods for intrusion detection systems: A survey // Applied Sciences. 2019. V. 9. N 20. P. 4396. https://doi.org/10.3390/app9204396Liu H., Lang B. Machine learning and deep learning methods for intrusion detection systems: A survey // Applied Sciences. 2019. V. 9. N 20. P. 4396. https://doi.org/10.3390/app9204396Sultana N., Chilamkurti N., Peng W., Alhadad R. Survey on SDN based network intrusion detection system using machine learning approaches // Peer-to-Peer Networking and Applications. 2019. V. 12. N 2. P. 493–501. https://doi.org/10.1007/s12083-017-0630-0Sultana N., Chilamkurti N., Peng W., Alhadad R. Survey on SDN based network intrusion detection system using machine learning approaches // Peer-to-Peer Networking and Applications. 2019. V. 12. N 2. P. 493–501. https://doi.org/10.1007/s12083-017-0630-0Sandhu U.A., Haider S., Naseer S., Ateeb O.U. A survey of intrusion detection & prevention techniques // Proc. of the 2011 International Conference on Information Communication and Management (IPCSIT). V. 16. 2011. P. 66–71.Sandhu U.A., Haider S., Naseer S., Ateeb O.U. A survey of intrusion detection & prevention techniques // Proc. of the 2011 International Conference on Information Communication and Management (IPCSIT). V. 16. 2011. P. 66–71.Aldweesh A., Derhab A., Emam A.Z. Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues // Knowledge-Based Systems. 2020. V. 189. P. 105124. https://doi.org/10.1016/j.knosys.2019.105124Aldweesh A., Derhab A., Emam A.Z. Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues // Knowledge-Based Systems. 2020. V. 189. P. 105124. https://doi.org/10.1016/j.knosys.2019.105124Reddy G.T., Reddy M.P.K., Lakshmanna K., Kaluri R., Rajput D.S., Srivastava G., Baker T. Analysis of dimensionality reduction techniques on big data // IEEE Access. 2020. V. 8. P. 54776–54788. https://doi.org/10.1109/ACCESS.2020.2980942Reddy G.T., Reddy M.P.K., Lakshmanna K., Kaluri R., Rajput D.S., Srivastava G., Baker T. Analysis of dimensionality reduction techniques on big data // IEEE Access. 2020. V. 8. P. 54776–54788. https://doi.org/10.1109/ACCESS.2020.2980942Varma P.R.K., Kumari V.V., Kumar S.S. A survey of feature selection techniques in intrusion detection system: A soft computing perspective // Advances in Intelligent Systems and Computing. 2018. V. 710. P. 785–793. https://doi.org/10.1007/978-981-10-7871-2_75Varma P.R.K., Kumari V.V., Kumar S.S. A survey of feature selection techniques in intrusion detection system: A soft computing perspective // Advances in Intelligent Systems and Computing. 2018. V. 710. P. 785–793. https://doi.org/10.1007/978-981-10-7871-2_75Almusallam N.Y., Tari Z., Bertok P., Zomaya A.Y. Dimensionality reduction for intrusion detection systems in multi-data streams—A review and proposal of unsupervised feature selection scheme // Emergence Complexity and Computation. 2017. V. 24. P. 467–487. https://doi.org/10.1007/978-3-319-46376-6_22Almusallam N.Y., Tari Z., Bertok P., Zomaya A.Y. Dimensionality reduction for intrusion detection systems in multi-data streams—A review and proposal of unsupervised feature selection scheme // Emergence Complexity and Computation. 2017. V. 24. P. 467–487. https://doi.org/10.1007/978-3-319-46376-6_22Sabar N.R., Yi X., Song A. A bi-objective hyper-heuristic support vector machines for big data cyber-security // IEEE Access. 2 0 1 8. V. 6. P. 1 0 4 2 1 – 1 0 4 3 1. https://doi.org/10.1109/ACCESS.2018.2801792Sabar N.R., Yi X., Song A. A bi-objective hyper-heuristic support vector machines for big data cyber-security // IEEE Access. 2 0 1 8. V. 6. P. 1 0 4 2 1 – 1 0 4 3 1. https://doi.org/10.1109/ACCESS.2018.2801792Aswanandini R., Muthumani N. Multi-objective hyper-heuristic improved particle swarm optimization based configuration of support vector machines for big data cyber security // International Journal of Innovative Technology and Exploring Engineering. 2019. V. 8. N 12. P. 3892–3897. https://doi.org/10.35940/ijitee.L3401.1081219Aswanandini R., Muthumani N. Multi-objective hyper-heuristic improved particle swarm optimization based configuration of support vector machines for big data cyber security // International Journal of Innovative Technology and Exploring Engineering. 2019. V. 8. N 12. P. 3892–3897. https://doi.org/10.35940/ijitee.L3401.1081219Vasan K.K., Surendiran B. Dimensionality reduction using principal component analysis for network intrusion detection // Perspectives in Science. 2016. V. 8. P. 510–512. https://doi.org/10.1016/j.pisc.2016.05.010Vasan K.K., Surendiran B. Dimensionality reduction using principal component analysis for network intrusion detection // Perspectives in Science. 2016. V. 8. P. 510–512. https://doi.org/10.1016/j.pisc.2016.05.010Salo F., Nassif A.B., Essex A. Dimensionality reduction with IG-PCA and ensemble classifier for network intrusion detection // Computer Networks. 2019. V. 148. P. 164–175. https://doi.org/10.1016/j.comnet.2018.11.010Salo F., Nassif A.B., Essex A. Dimensionality reduction with IG-PCA and ensemble classifier for network intrusion detection // Computer Networks. 2019. V. 148. P. 164–175. https://doi.org/10.1016/j.comnet.2018.11.010Moustakidis S., Karlsson P. A Novel feature extraction methodology using Siamese convolutional neural networks for intrusion detection // Cybersecurity. 2020. V. 3. N 1. P. 16. https://doi.org/10.1186/s42400-020-00056-4Moustakidis S., Karlsson P. A Novel feature extraction methodology using Siamese convolutional neural networks for intrusion detection // Cybersecurity. 2020. V. 3. N 1. P. 16. https://doi.org/10.1186/s42400-020-00056-4Zhou Y., Cheng G., Jiang S., Dai M. Building an efficient intrusion detection system based on feature selection and ensemble classifier // Computer Networks. 2020. V. 174. P. 107247. https://doi.org/10.1016/j.comnet.2020.107247Zhou Y., Cheng G., Jiang S., Dai M. Building an efficient intrusion detection system based on feature selection and ensemble classifier // Computer Networks. 2020. V. 174. P. 107247. https://doi.org/10.1016/j.comnet.2020.107247Swarna Priya R.M., Maddikunta P.K.R., Parimala M., Koppu S., Gadekallu T.R., Chowdhary C.L., Alazab M. An effective feature engineering for DNN using hybrid PCA-GWO for intrusion detection in IoMT architecture // Computer Communications. 2020. V. 160. P. 139–149. https://doi.org/10.1016/j.comcom.2020.05.048Swarna Priya R.M., Maddikunta P.K.R., Parimala M., Koppu S., Gadekallu T.R., Chowdhary C.L., Alazab M. An effective feature engineering for DNN using hybrid PCA-GWO for intrusion detection in IoMT architecture // Computer Communications. 2020. V. 160. P. 139–149. https://doi.org/10.1016/j.comcom.2020.05.048Khare N., Devan P., Chowdhary C.L., Bhattacharya S., Singh G., Singh S., Yoon B. SMO-DNN: Spider monkey optimization and deep neural network hybrid classifier model for intrusion detection // Electronics. 2020. V. 9. N 4. P. 692. https://doi.org/10.3390/electronics9040692Khare N., Devan P., Chowdhary C.L., Bhattacharya S., Singh G., Singh S., Yoon B. SMO-DNN: Spider monkey optimization and deep neural network hybrid classifier model for intrusion detection // Electronics. 2020. V. 9. N 4. P. 692. https://doi.org/10.3390/electronics9040692

The authors declare that there are no conflicts of interest present.