Telsiz Duyarga Ağlarda Byzantine Saldırılarının Topluluk Öğrenme-tabanlı Tespiti

Year 2020, , 905 - 918, 22.09.2020

Vahid Akram Pelin Yıldırım Taşer

https://doi.org/10.21205/deufmd.2020226624

Cited By: 2

Abstract

TTelsiz duyarga ağlar (TDA)’da düğümler arasında güvenilir iletişimin sağlanması ve doğru verilerin toplanması birçok açıdan hayati önem taşımaktadır. TDA’ların merkezi iletişim altyapısı olmadığından dolayı, bu ağlar çeşitli saldırılara maruz kalabilmektedirler. TDA’larda yaygın saldırı türlerinden birisi olan Bizans saldırısında, saldırgan ağ alanına yeni bir düğüm ekleyip sahte veriler üreterek ağın güvenilirliğini düşürebilmektedir. Bu çalışma, TDA’da Bizans saldırılarının tespitine yönelik iki yeni topluluk tabanlı yaklaşım önermektedir. Önerilen bu yaklaşımlar, 3 farklı geleneksel sınıflandırma algoritmasının (Naive Bayes, karar ağacı (C4.5) ve k-en yakın komşuluk (İng. k-NN)) voting ve stacking yönetimleri ile bir araya getirilmesinden meydana gelmektedir. Ayrıca, deneysel çalışmalar kapsamında, önerilen iki yeni yaklaşımın yanı sıra, mevcut topluluk öğrenmesi yaklaşımları (C4.5 tabanlı Bagging (Bagging(C4.5)) ve Boosting (AdaBoost)) ile geleneksel algoritmalar (Naive Bayes, C4.5 ve k-NN) da, 66 IRIS düğümünden (60 normal, 6 saldırgan) oluşan örnek ağ üzerinde uygulanmıştır. Her bir algoritmadan elde edilen sınıflandırma sonuçları, doğruluk oranı ve f-ölçüm değerlerine göre karşılaştırılmıştır. Test yatağından elde edilen sonuçlar göstermektedir ki, topluluk tabanlı yöntemler, TDA’da Bizans saldırılarının tespitinde %98.48 doğruluk oranına ulaşırken, geleneksel (tek bir sınıflandırma modeli kullanan) yöntemler %96.97 ile sınırlı kalmaktadır. Çok sayıda düğüm içeren daha büyük ağlarda, bu oranların arasındaki fark artabilir.

Keywords

Byzantine Saldırıları, Makine Öğrenmesi, Sınıflandırma, Telsiz Duyarga Ağlar, Topluluk Öğrenmesi

Ensemble Learning-based Method for Detection of Byzantine Attacks in Wireless Sensor Networks

Abstract

Reliable communication and accurate data collection are crucial tasks in Wireless Sensor Networks (WSNs). Due to the lack of having no central communication infrastructure, WSNs can be exposed to various attacks. One of the common attack types in WSNs is Byzantine attack, in which the attacker can reduce the reliability of the network by adding new nodes to the network area and sending fake data. This study proposes two ensemble-based approaches for detecting the Byzantine attacks in WSNs. The proposed approaches combine three different traditional classification algorithms (Naive Bayes, decision tree (C4.5), and k-NN) with voting and stacking methods. In addition to the proposed methods, the current ensemble learning approaches (C4.5 based Bagging (Bagging(C4.5)) and Boosting (AdaBoost)) and the traditional algorithms (Naive Bayes, C4.5 and k-NN) were applied on a sample network of 66 IRIS nodes (60 normal, 6 malicious) within experimental studies. The classification results obtained from each algorithm were compared according to the accuracy rate and f-measure values. The results gathered from the testbed show that the ensemble-based methods achieve up to 98.48% accuracy rate for detection of the Byzantine attacks in the sample network while this ratio for the traditional methods is limited to the 96.97%. In large networks with more nodes, the difference among these ratios may increase.

Keywords

Byzantine Attacks, Classification, Ensemble Learning, Machine Learning, Wireless Sensor Networks

References

• [1] Akyildiz, I. F., Su, W., Sankarasubramaniam, Y., Cayirci, E. 2002. Wireless sensor networks: a survey. Computer networks, Cilt. 38(4), s. 393-422.
• [2] Yu, L., Wang, N., Meng, X. 2005. Real-time forest fire detection with wireless sensor networks. International Conference on Wireless Communications, Networking and Mobile Computing, Cilt. 2, s. 1214-1217, IEEE.
• [3] Arslan, S., Challenger, M., Dagdeviren, O. 2017, Wireless sensor network based fire detection system for libraries. International Conference on Computer Science and Engineering (UBMK) s. 271-276, IEEE.
• [4] Karimpour, N., Karaduman, B., Ural, A., Challenger, M., Dagdeviren, O, 2019, IoT based Hand Hygiene Compliance Monitoring. In International Symposium on Networks, Computers and Communications (ISNCC), s. 1-6, IEEE.
• [5] Karlof, C., Wagner, D. 2003, Secure routing in wireless sensor networks: Attacks and countermeasures. Ad hoc networks, Cilt 1(2-3), s. 293-315.
• [6] Dağdeviren, O., Akram, V. K. 2017. TinyOS Tabanlı Telsiz Duyarga Ağları için Bir Konumlandırma ve k-Bağlılık Denetleme Sistemi. Bilişim Teknolojileri Dergisi, Cilt. 10(2), s.139-152.
• [7] Pathan, A. S. K., Lee, H. W., Hong, C. S. 2006. Security in wireless sensor networks: issues and challenges. 8th International Conference Advanced Communication Technology, Cilt. 2, s. 1043-1048. IEEE.
• [8] Rawat, A. S., Anand, P., Chen, H., Varshney, P. K. 2010, Collaborative spectrum sensing in the presence of Byzantine attacks in cognitive radio networks. IEEE Transactions on Signal Processing, Cilt. 59(2), s. 774-786.
• [9] Padmavathi, D. G., Shanmugapriya, M. 2009. A survey of attacks, security mechanisms and challenges in wireless sensor networks. arXiv preprint arXiv:0909.0576.
• [10] Salam, M. A., Halemani, N. 2016. Performance evaluation of wireless sensor network under hello flood attack. International Journal of Computer networks & Communications (IJCNC), Cilt 8(2).
• [11] Abidoye, A. P., Obagbuwa, I. C. 2017. DDoS attacks in WSNs: detection and countermeasures. IET Wireless Sensor Systems, Cilt. 8(2), s. 52-59.
• [12] Otoum, S., Kantarci, B., Mouftah, H. T. 2017. Hierarchical trust-based black-hole detection in WSN-based smart grid monitoring. 2017 IEEE International Conference on Communications (ICC) (pp. 1-6). IEEE.
• [13] Amish, P., Vaghela, V. B. 2016. Detection and prevention of wormhole attack in wireless sensor network using AOMDV protocol. Procedia computer science, Cilt. 79, s. 700-707.
• [14] Alsaedi, N., Hashim, F., Sali, A., Rokhani, F. Z. 2017. Detecting sybil attacks in clustered wireless sensor networks based on energy trust system (ETS). Computer communications, Cilt. 110, s. 75-82.
• [15] Ren, J., Zhang, Y., Zhang, K., Shen, X. 2016. Adaptive and channel-aware detection of selective forwarding attacks in wireless sensor networks. IEEE Transactions on Wireless Communications, Cilt. 15(5), s. 3718-3731.
• [16] Oh, S. H., Hong, C. O., Choi, Y. H. 2012. A malicious and malfunctioning node detection scheme for wireless sensor networks. Wireless sensor network, Cilt. 4(03), s. 84-90.
• [17] Alizadeh, H., Sharifi, A. A., Niya, M., Javad, M., Seyedarabi, H. 2017. Attack-aware cooperative spectrum sensing in cognitive radio networks under Byzantine attack. Journal of Communication Engineering, Cilt. 6(1), s. 81-98.
• [18] He, X., Dai, H., Ning, P. 2013. A Byzantine attack defender in cognitive radio networks: The conditional frequency check. IEEE Transactions on Wireless Communications, Cilt. 12(5), s. 2512-2523.
• [19] Zhang, P., Koh, J. Y., Lin, S., Nevat, I. 2014. Distributed event detection under byzantine attack in wireless sensor networks. 2014 IEEE Ninth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP) s. 1-6, IEEE.
• [20] Curiac, D. I., Banias, O., Dragan, F., Volosencu, C., Dranga, O. 2007. Malicious node detection in wireless sensor networks using an autoregression technique. In International Conference on Networking and Services (ICNS'07) s. 83-83. IEEE.
• [21] Wang, W., Li, H., Sun, Y., Han, Z. 2009. Securing collaborative spectrum sensing against untrustworthy secondary users in cognitive radio networks. EURASIP Journal on Advances in Signal Processing, 2010, s. 1-15.
• [22] Kaligineedi, P., Khabbazian, M., Bhargava, V. K. 2010. Malicious user detection in a cognitive radio cooperative sensing system. IEEE Transactions on Wireless Communications, Cilt. 9(8), s. 2488-2497.
• [23] Li, H., Han, Z. 2010. Catch me if you can: An abnormality detection approach for collaborative spectrum sensing in cognitive radio networks. IEEE Transactions on Wireless Communications, Cilt. 9(11), s. 3554-3565.
• [24] Adelantado, F., Verikoukis, C. 2011. A non-parametric statistical approach for malicious users detection in cognitive wireless ad-hoc networks. 2011 IEEE international conference on communications (ICC) s. 1-5. IEEE.
• [25] Min, A. W., Shin, K. G., Hu, X. 2009. Attack-tolerant distributed sensing for dynamic spectrum access networks. 17th IEEE International Conference on Network Protocols, s. 294-303. IEEE.
• [26] Li, S., Zhu, H., Yang, B., Chen, C., Guan, X. 2011. Believe yourself: A user-centric misbehavior detection scheme for secure collaborative spectrum sensing. 2011 IEEE International Conference on Communications (ICC), s. 1-5. IEEE.
• [27] Mukherjee, S., Neelam, S. 2012. Intrusion Detection using Naive Bayes Classifier with Feature Reduction, Procedia Technology, Cilt. 4, s. 119-128. DOI: 1 0.1016/j.protcy.2012.05.017
• [28] Hodo, E., Bellekens, X., Hamilton, A., Dubouilh, P.L. 2016. Threat analysis of IoT networks using artificial neural network intrusion detection system. 2016 International Symposium on Networks, Computers and Communications (ISNCC), 11-13 Mayıs, Yasmin Hammamet, 1-6.
• [29] Jim, L.E., Chacko, J. 2019. Decision Tree based AIS strategy for Intrusion Detection in MANET. 2019 IEEE Region 10 Conference (TENCON), 17-20 Ekim, Kochi, 1191-1195.
• [30] Yıldırım, P., Birant, D. 2018. The Relative Performance of Deep Learning and Ensemble Learning for Textile Object Classification. 2018 3rd International Conference on Computer Science and Engineering (UBMK), 20-23 Eylül, Saraybosna, 22-26.
• [31] Tama, B.A., Rhee, K. 2016. Classifier Ensemble Design with Rotation Forest to Enhance Attack Detection of IDS in Wireless Network. 2016 11th Asia Joint Conference on Information Security (AsiaJCIS), 4-5 Ağustos, Fukuoka, 87-91.
• [32] Hu, W., Hu, W., Maybank, S. 2008. AdaBoost-Based Algorithm for Network Intrusion Detection, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Cilt. 38, s. 577-583. DOI: 10.1109/TSMCB.2007.914695
• [33] Chebrolu, S., Abraham, A., Thomas, J.P. 2005. Feature deduction and ensemble design of intrusion detection systems, Computers & Security, Cilt. 24, s. 295-307. DOI: 10.1016/j.cose.2004.09.008
• [34] Cabrera, J.B.D., Guiterrez, C., Mehra, R.K. 2008. Ensemble methods for anomaly detection and distributed intrusion detection in Mobile Ad-Hoc Networks, Information Fusion, Cilt. 9, s. 96-119. DOI: 10.1016/j.inffus.2007.03.001
• [35] Ma, T., Wang, F., Cheng, J., Yu, Y., Chen, X. 2016. A Hybrid Spectral Clustering and Deep Neural Network Ensemble Algorithm for Intrusion Detection in Sensor Networks, Sensors, Cilt. 16, s. 1-23. DOI: 10.3390/s16101701
• [36] Yildirim, P., Birant, K.U., Radevski, V., Kut, A., Birant, D. 2018. Comparative analysis of ensemble learning methods for signal classification. 26th Signal Processing and Communications Applications Conference (SIU), 2-5 Mayıs, İzmir, 1-4.
• [37] Yu, L., Shouyang, W., Lai, K.K. 2008. Credit risk assessment with a multistage neural network ensemble learning approach, Expert Systems with Applications, Cilt. 34, s. 1434–1444. DOI:10.1016/j.eswa.2007.01.009
• [38] Yu, H., Ni, J. 2014. An Improved Ensemble Learning Method for Classifying High-Dimensional and Imbalanced Biomedicine Data, IEEE/ACM Trans Comput Biol Bioinform, Cilt. 11, s. 657-666. DOI: 10.1109/TCBB.2014.2306838
• [39] Wang, G., Hao, J, Ma, J., Jiang, H. 2011. A comparative assessment of ensemble learning for credit scoring, Expert Systems with Applications, Cilt. 38, s. 223-230. DOI: 10.1016/j.eswa.2010.06.048
• [40] Weka. https://www.cs.waikato.ac.nz/ml/weka/ (Erişim Tarihi: 08.03.2020).