Makine Öğrenme Metotları Kullanılarak KSA Ddos Saldırıları Tespiti

Abstract

Son yıllardaki teknolojik gelişmelerle birlikte Kablosuz Sensör Ağlarının (KSA) kullanım alanları ve popülaritesi artmaktadır. Özellikle IoT teknolojisiyle birlikte çalışan sensör ağları; akıllı arabalar, akıllı evler, akıllı şehir gibi sivil uygulama alanlarında, askeri alanlarda ve endüstri-sanayide kullanılmaktadır [1]. Kullanıldığı alanlar itibari ile saldırılara açık bir yapıya sahiptir. Bu saldırıların bazı fiziksel bazıları ise programsaldır. Hayat kalitesini arttıran ve hayatı kolaylaştıran bu teknolojilere yapılan saldırıları önlemek için bu alanda çeşit çalışmalar yapılmaktadır. Bu çalışmada KSA ağ saldırıları veri seti alınarak yapay zeka teknolojisinin alt dalı olan makine öğrenme modelleri ile analiz edilmiştir. Bu çalışmada WSN-DS saldırı veri seti kullanılmıştır. Veri seti, NS 2 benzetim ortamında oluşturulmuştur. Veri seti Grayhole, Blackhole, Flooding, TDMA gibi ağ saldırı trafiklerinden ve normal ağ trafiğinden oluşmaktadır. Bu veri seti makine öğrenme modellerinden gözetimli ve gözetimsiz modellerle incelenmiştir. Gözetimli öğrenme modellerinden; Decision Tree (J48), Random Forest, Naive Bayes algoritmalarıyla incelenmiş, gözetimsiz öğrenme modellerinden; Expectation Maximization (EM), Simple Kmeans, Filtered Clusterer,Canopy algoritmaları ile incelenmiştir. Sonuçları uygulama bölümünden tablolarla gösterilmiştir. Çalışma java tabanlı Weka 3.8.3 kullanılarak gerçekleştirilmiştir.

Keywords

• KSA
• ddos saldırıları
• makine öğrenmesi siber güvenlik
• NS2

Detecting Wsn Ddos Attacks Using Machine Learning Methods

Abstract

With the technological developments in recent years, the usage areas and popularity of Wireless Sensor Networks (WSNs) are increasing. Especially sensor networks working with IoT technology; It is used in civil application areas such as smart cars, smart homes, smart city, military fields and industry. In terms of the areas in which they are used, WSNs have a structure that is open to attacks. Some of these attacks are physical and some are programmatic. Various studies are carried out in this area to prevent attacks on these technologies that increase the quality of life and make life easier. In this study, WSNs attacks data set were taken and analyzed with machine learning models, which are sub-branches of artificial intelligence technology. The WSN-DS attack dataset used was created in the NS 2 simulation environment and consists of network attack traffics such as Grayhole, Blackhole, Flooding, TDMA and normal network traffic. In this study, the data set is analyzed with Supervised learning models (Decision Tree (J48), Random Forest, Naive Bayes) and Unsupervised learning models (Expectation Maximization (EM), Simple Kmeans, Filtered Clusterer, Canopy). The study was carried out using java based Weka 3.8.3, and the experimental results obtained are presented in detail.

Keywords

• WSNs
• ddos attacks
• machine learning
• cyber security
• NS2

References

1. [1]. M. Dener and O. Bay, "TeenySec: a new data link layer security protocol for WSNs", Security and Communication Networks, 9(18), 5882-5891, 2016. Available: 10.1002/sec.1743.
2. [2]. D. Deif and Y. Gadallah, "An ant colony optimization approach for the deployment of reliable wireless sensor networks", IEEE Access, 5, 10744-10756, 2017. Available: 10.1109/access.2017.2711484.
3. [3]. Z. Sheng, C. Mahapatra, C. Zhu and V. Leung, "Recent advances in ındustrial wireless sensor networks toward efficient management in IoT", IEEE Access, 3, 622-637, 2015. Available: 10.1109/access.2015.2435000.
4. [4]. M. Abazeed et al., "A review of secure routing approaches for current and next-generation wireless multimedia sensor networks", International Journal of Distributed Sensor Networks, 2015, 1-22, 2015. Available: 10.1155/2015/524038.
5. [5]. M. Selvi, K. Thangaramya, S. Ganapathy, K. Kulothungan, H. Khannah Nehemiah and A. Kannan, "An energy aware trust based secure routing algorithm for effective communication in wireless sensor networks", Wireless Personal Communications, 105 (4), 1475-1490, 2019. Available: 10.1007/s11277-019-06155-x.
6. [6]. C. Karlof and D. Wagner, "Secure routing in wireless sensor networks: attacks and countermeasures", Ad Hoc Networks,1 (2-3), 293-315, 2003. Available: 10.1016/s1570-8705(03)00008-8.
7. [7]. M. Dener, "Security analysis in wireless sensor networks", International Journal of Distributed Sensor Networks, 10 (10), 303501, 2014. Available: 10.1155/2014/303501.
8. [8]. W. R. Heinzelman, A. Chandrakasan, and H. Balakrishnan, “Energy-efficient communication protocol for wireless microsensor networks,” in Proceedings of the 33rd IEEE Annual Hawaii International Conference on System Sciences, 1–10, Maui, Hawaii, USA, January 2000.

9. [9]. S. Tyagi and N. Kumar, “A systematic review on clustering and routing techniques based upon LEACH protocol for wireless sensor networks,” Journal of Network and Computer Applications, 36 (2), 623–645, 2013.
10. [10]. S.Kannan,T.Maragatham,S.Karthik and V. P. Arunachalam,“A study of attacks,attack detection and preevention methods in proactive and reactive routing protocols”International Business Management, 5(3), 4178-183,2011.
11. [11]. F. Tseng, L. Chou, & H. Chao, “A survey of black hole attacks in wireless mobile ad hoc networks”. Human Centric Computing Information Sciences 1(4),2011. https://doi.org/10.1186/2192-1962-1-4.
12. [12]. I. Almomani and B. Al-Kasasbeh, "Performance analysis of LEACH protocol under Denial of Service attacks," 2015 6th International Conference on Information and Communication Systems (ICICS), 292-297, 2015. doi: 10.1109/IACS.2015.7103191.
13. [13]. “Makine Öğrenmesi Nedir ?”, Medium, 2020. [Online]. Available:https://medium.com/t%C3%BCrkiye/makine%C3%B6%C4%9Frenmesi-nedir-20dee450b56e. [Accessed: 24- Jun- 2020].
14. [14]. O. Salman, I. Elhajj, A. Chehab and A. Kayssi, "A machine learning based framework for IoT device identification and abnormal traffic detection", Trans on Emerging Telecomm. Techn, 2019. Available: 10.1002/ett.3743.
15. [15]. S. Patil and U. Kulkarni, "Accuracy Prediction for Distributed Decision Tree using Machine Learning approach”, 3rd International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, pp. 1365-1371, 2019. doi: 10.1109/ICOEI.2019.8862580.
16. [16]. I. Almomami, B. Al-Kasasbeh, M. Al-Akhras, “ WSN-DS: A Dataset for Intrusion Detection Systems in Wireless Sensor Networks”, Journal of Sensors, 1-16, 2016. http://dx.doi.org/10.1155/2016/4731953.