سیستم تشخیص نفوذ بهبود یافته مبتنی بر الگوریتم ژنتیک خود تطبیق جزیره ای برای حل ماشین بردار پشتیبان به صورت یادگیری چندهسته ای با کد کننده های خودکار ن

نوع مقاله: مقاله پژوهشی

نویسندگان

1 گروه کامپیوتر، واحد نیشابور، دانشگاه آزاد اسلامی، نیشابور، ایران

2 گروه کامپیوتر،دانشکده فنی و مهندسی، ,واحد مشهد، دانشگاه آزاد اسلامی، مشهد، ایران

3 گروه کامپیوتر،واحد نیشابور، دانشگاه آزاد اسلامی،نیشابور،ایران

چکیده

نفوذ به سیستم‌ها از طریق زیرساخت شبکه و اینترنت یکی از چالش‌های امنیتی است که دنیای فناوری اطلاعات و ارتباطات را با آن روبرو کرده است و می‌تواند منجر به تخریب سیستم‌ها و دسترسی به داده‌ها و اطلاعات گردد. در این مقاله یک مدل ماشین بردار پشتیبان که هسته‌های آن وزن‌دار شده به همراه پارامترهای هسته‌های ماشین بردار پشتیبان برای سیستم تشخیص نفوذ ارائه شده است. با توجه به پیچیدگی محاسباتی این مدل، روش الگوریتم ژنتیک جزیره‌ای پویای خود تطبیقی پیشنهاد شده تا پیچیدگی محاسبات را کم نماید. در این روش از اتوانکودر نیز برای کاهش حجم داده‌ها استفاده شده است. روش پیشنهادی یک روش ترکیبی پیشنهادی مبتنی بر اتوانکودر و ماشین بردار پشتیبان بهبودیافته با الگوریتم ژنتیک جزیره‌ای پویای خود تطبیق است که دقت بهتری در مسائل تشخیص نفوذ را نشان می­دهد. نتایج شبیه­سازی بر روی مجموعه داده DARPA برای تست عملکرد مورد استفاده قرار گرفته است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Developing A Distributed Self Adaptive Genetic Algorithm with Migration to improve performance of Support Vector Machine for Intrusion Detection

نویسندگان [English]

  • Elaheh Faghihnia 1
  • Seyed Reza Kamel Tabakh Farizni 2
  • Maryam Kheirabadi 3
1 Department of computer, Neyshabur Branch , Islamic Azad University, Neyshabur , Iran.
2 Department of computer Engineering, Mashhad Branch , Islamic Azad University, Mashhad , Iran
3 Department of computer, Neyshabur Branch , Islamic Azad University, Neyshabur , Iran.
چکیده [English]

Today easy data access through the network has made it possible to steal them. Therefore, the security of computer systems has become increasingly important. Intrusion Detection Systems . as the last line of computer defense, can play an important role in attack resistance and their efficiencies has direct impact on network security. The Intrusion Detection Systems must extract the necessary strategies based on the connections and use them to detect new connections. Support Vector Machine is a Machine Learning method that it is popular to extract intrusion strategies in past decade. Although simplification of SVM returned it to popular method but it has constraints such as senility to kernel selection and it has not any optimization mechanism to determine the best of them. We model it as using of several kernels simultaneously and different weighting to them and dynamic SVM parameters. Due to the high complexity of this problem, conventional optimization methods are not able to solve it. Therefore, we propose a Distributed Self Adaptive Genetic Algorithm with Migration. On the other hand, due to the high volume of data in such issues, Autoencoder has been used to reduce data. The proposed approach is a hybrid method based on Autoencoder and improved Support Vector Machine with Distributed Self Adaptive Genetic Algorithm with Migration that it is evaluated by its execution on data set. The experimental results have demonstrated that the proposed system exhibits a high performance for attack detection based on precision and recall and it low time for intrusion.

کلیدواژه‌ها [English]

  • Intrusion Detection Systems (IDS)
  • Support vector machine (SVM)
  • Big data
  • island genetic algorithm (IGA). self-adaptive genetic algorithm (SAGA)
  • distributed self-adaptive genetic algorithm (DSAGA)
[1]    A. Almomani, M. Alauthman, F. Albalas, O. Dorgham, A. Obeidat "An online intrusion detection system to cloud computing based on NeuCube algorithms", International Journal of Cloud Applications and Computing, vol. 8, no. 2, pp.1042-1059, 2018 (doi:10.4018/IJCAC.2018040105).

[2]    S. A. Mulay, P. Devale, G. Garje, "Intrusion detection system using support vector machine and decision tree", International Journal of Computer Applications,vol. 3, no.3, pp. 40-43, 2010 (doi:10.5120/758-993).

[3]    W. Laftah Al-Yaseen,"Improving intrusion detection system by developing feature selection model based on firefly algorithm and support vector machine", IAENG International Journal of Computer Science, vol. 46, no. 4, pp. 534-540, 2019 (doi: IJCS_46_4_04).

[4]    M. R. G. Raman, N. Somu, S. Jagarapu, T. Manghnani, T. Selvam, K. Krithivasan,V. S. S. Sriram, "An efficient intrusion detection technique based on support vector machine and improved binary gravitational search algorithm", Artificial Intelligence Review, vol. 53, pp. 3255-3286, 2019 (doi:10.1007/s.10462-019-09762-z).

[5]    M. Ramkumar, M. Manikandan, K. Sathish Kumar, R. K. Kumar, "Intrusion detection in manets using support vector machine with ant colony optimization"  ICTACT journals on data csience and machine learning, vol. 1, no.1, 2019.

[6]    J. C. Badajena, C. Rout, "Incorporating hidden markov model into anomaly detection technique for network intrusion detection", International Journal of Computer Applications, vol. 53, no. 11, 2012 (doi: 10.5120/84­69-­2395).

[7]    P. Dorogovs, A. Borisov, A. Romanovs, "Building an intrusion detection system for it security based on data mining techniques", Applied Computer Systems, vol. 45, no. 1, pp. 43-48, 2011 (doi: 10.2478/v10143-011-0­0­40-3).

[8]    S. Shirbhate, S. Sherekar and, V. Thakare, " Performance evaluation of PCA filter in clustered based intrusion detection system",  Proceeding of the IEEE/ICESC, pp. 217-221, Nagpur, India ,Feb. 2014 (doi: 10.1­10­9­/I­C­E­S­C.2014.100).

[9]    D. Gupta, S. Singhal, S. Malik, A. Singh, "Network intrusion detection system using various data mining techniques", Proceeding of the IEEE/(RAINS), pp. 1-6,  Bangalore, India, May. 2016 (doi: 10.110­9/RA­IN­S.2­016.7764418).

[10] E. Ariafar, R. Kiani, "Intrusion detection system using an optimized framework based on datamining techniques", Proceeding of the IEEE/KBEI, pp. 0785-0791, Tehran, Iran, Dec. 2017 (doi: 10.1109/KBE­I.­201­7.8324903).

[11] J. A. Sukumar, I. Pranav,MM. Neetish, J. Narayanan, "Network intrusion detection using improved genetic k-means algorithm", Proceeding of the IEEE/ICACCI, pp. 2441-2446, Bangalore, India, Sept. 2018 (doi: 10.­1109­/ICACCI.2018.8554710).

[12] P. S. Bhattacharjee, A. K. M, Fujail, A. A. Begum, "Intrusion detection system for NSL-KDD data set using vectorised fitness function in genetic algorithm", Advances in Computational Sciences and Technolog.,vol. 10, no. 2, pp. 235-246, 2017.

[13] J. Ghasemi, J. Esmaeily, R. Moradinezhad, "Intrusion detection system using an optimized kernel extreme learning machine and efficient features", Sådhanå,vol. 45, no. 2, pp.1-9, 2020(doi: 10.1007/s12046-019-1230-x).

[14] D. Pal, A. Parashar, "Improved genetic algorithm for intrusion detection system", Proceeding of the IEEE/CI­C­N, pp. 835-839, Bhopal, India, Nov. 2014 (doi: 10.1109/CICN.2014.178).

[15] Y. Danane, T. Parvat, "Intrusion detection system using fuzzy genetic algorithm", Proceeding of the IEEE/ ICPC , pp. 1-5,   St. Louis,  Missouri,  USA, March. 2015 (doi: 10.1109/PERVASIVE.2015.7086963).

[16] A. F. A. Pinem, E. B. Setiawan, "Implementation of classification and regression tree (CART) and fuzzy logic algorithm for intrusion detection system", Proceeding of the IEEE/ ICoICT, pp. 266-271,  Bali, Indonesia, May. 2015 (doi: 10.1109/ICoICT.2015.7231434).

[17] S. Sahu, B. M. Mehtre, "Network intrusion detection system using J48 decision tree", Proceeding of the IEEE/ ICACCI, pp. 2023-2026, Kochi, India, Aug. 2015 (doi: 10.1109/ICACCI.2015.7275914).

[18] S. M. H. Bamakan, H. Wang, Y. Shi, " Ramp loss k-support vector classification-regression; a robust and sparse multi-class approach to the intrusion detection problem", Knowledge-Based Systems, vol.126, pp. 113-126, 2017 (doi: 10.1016/j.knosys.2017.03.012).

[19] C. A. Catania, C. G. Garino, "Automatic network intrusion detection: Current techniques and open issues", Computers & Electrical Engineering, vol. 38, no. 5, pp. 1062-1072, 2012 (doi: 10.1016/j.compeleceng.20­1­2.­0­­5.013).

[20] S. Aljawarneh, M. Aldwairi, M. B. Yassein, "Anomaly-based intrusion detection system through feature selection analysis and building hybrid efficient model", Journal of Computational Science, vol. 25, pp. 152-160, 2018 (doi: 10.1016/j.jocs.2017.03.006).

[21] G. Sandhya, A. Julian, "Intrusion detection in wireless sensor network using genetic K-means algorithm", Proceeding of the IEEE/ ICACCCT, pp. 1791-1794, Ramanathapuram, India, May. 2014 (doi: 10.1109/IC­AC­CC­T.2014.7019418).

[22] M. Sharma, K. Jindal, A.Kumar, "Intrusion detection system using Bayesian approach", International Journal of Computer Application, vol. 48, no.5, pp. 29-33,2012.

[23] G. Sandhya, A. Julian, "Intrusion detection in wireless sensor network using genetic K-means algorithm",  Proceeding of the IEEE/ ICACCCT  pp. 1791-1794, Ramanathapuram, India, May. 2014 (doi: 10.1109/I­C­A­C­CC­T.2014.7019418).

[24] T. Yerong, S. Sai, X. Ke, L. Zhe, "Intrusion detection based on support vector machine using heuristic genetic algorithm", Proceeding of the IEEE/CSNT,  pp. 681-684, Bhopal, India,Apr. 2014 (doi: 10.1109/C­SNT.­20­1­4­.143).

[25] Q. Schueller, K. Basu, M. Younas, M. Patel, F. Ball, "A hierarchical intrusion detection system using support vector machine for SDN network in cloud data center", Proceeding of the IEEE/ITNAC), pp. 1-6. Sedney, Aust­ralia, Nov. 2018 (doi: 10.1109/ATNAC.2018.8615255).

[26] R. Vijayanand, D. Devaraj, B. Kannapiran, "Intrusion detection system for wireless mesh network using multiple support vector machine classifiers with genetic-algorithm-based feature selection", Computers and Security, vol. 77, pp. 304-314, 2018 (doi: doi.org/10.1016/j.cose.2018.04.010).

[27] M. G. Raman, N. Somu, K. Kirthivasan, R. Liscano, V. S. S. Sriram, "An efficient intrusion detection system based on hypergraph-genetic algorithm for parameter optimization and feature selection in support vector machine", Knowledge-Based Systems, vol. 134, pp. 1-12, 2011 (doi: 10.1016/j.knosys.2017.07.005).

[28] S. Mirjalili, "Genetic algorithm", Evolutionary Algorithms and Neural Networks, Part of the Studies in Computational Intelligence Book Series (SCI), vol.780, pp. 43-55, 2019 (doi: 10.1007/978-3-319-93025-1_4)

[29] M. Gharaibeh, C. Papadopoulos, "Darpa-2009 intrusion detection dataset report", Tech. Rep., 2014.