Güvenlik Duvarlarındaki Ağ Trafiği Log Kayıtlarının Analizinde Açıklanabilir Yapay Zekâ ve Derin Sinir Ağlarının Kullanımı: Karşılaştırmalı Bir Analiz

Yıl 2024, Cilt: 40 Sayı: 3, 587 - 608, 30.12.2024

Anıl Utku

Öz

İnternet kullanımında yaşanan hızlı büyüme, siber tehditlerin çeşitlenmesine ve karmaşıklığının artmasına neden olmuştur. Bu durum, özellikle ağ güvenliği konusunda daha gelişmiş ve dinamik çözümler geliştirilmesini zorunlu kılmaktadır. Geleneksel güvenlik yöntemleri, özellikle güvenlik duvarları, belirli kurallar çerçevesinde çalıştığından, yeni nesil siber tehditlere karşı yetersiz kalabilmektedir. Güvenlik duvarları, ağ trafiğini izleyerek potansiyel tehditleri tespit eden ve engelleyen önemli araçlar olarak uzun yıllardır kullanılmaktadır. Ancak, statik kurallara dayanan geleneksel güvenlik duvarları, karmaşık ve dinamik tehditleri algılamada yetersiz kalmakta ve yüksek oranda yanlış pozitif/negatif sonuçlar üretmektedir. Bu durum, daha esnek ve kendini sürekli olarak geliştirebilen yapay zekâ tabanlı güvenlik çözümlerine olan ihtiyacı artırmıştır. Bu çalışmada, açıklanabilir yapay zekâ ve DNN tabanlı bir derin öğrenme modeli kullanarak güvenlik duvarlarındaki ağ trafiği loglarının analiz edilmesi hedeflenmiştir. Geliştirilen DNN tabanlı model, RF, kNN, SVM, LR ve XGBoost gibi popüler makine öğrenmesi algoritmalarıyla karşılaştırılarak performansı değerlendirilmiştir. Deneysel sonuçlar, geliştirilen DNN tabanlı modelin %99,87 doğruluk oranıyla karşılaştırılan modellerden ve literatürdeki çalışmalardan daha başarılı olduğunu göstermiştir.

Anahtar Kelimeler

Açıklanabilir Yapay Zekâ, Derin Sinir Ağları, Makine Öğrenmesi, Derin Öğrenme, Ağ Trafiği Analizi

Kaynakça

• [1] Diwan, T. D. 2021. An investigation and analysis of cyber security information systems: latest trends and future suggestion. Information Technology in Industry, 9(2), 477-492.
• [2] Alsaqour, R., Motmi, A., Abdelhaq, M. 2021. A systematic study of network firewall and its implementation. International Journal of Computer Science & Network Security, 21(4), 199-208.
• [3] Islam, M. S., Uddin, M. A., Hossain, D. M. D., Ahmed, D. M. S., Moazzam, D. M. G. 2023. Analysis and evaluation of network and application security based on next generation firewall. International Journal of Computing and Digital Systems, 13(1), 193-202.
• [4] Anwar, R. W., Abdullah, T., Pastore, F. 2021. Firewall best practices for securing smart healthcare environment: A review. Applied Sciences, 11(19).
• [5] Varzaneh, M. R., Habbal, A., Dakkak, O. 2024. Firewalls and Internet of Things Security: A Survey. Current Trends in Computing, 1(1), 22-43.
• [6] Lyu, M., Gharakheili, H. H., Russell, C., Sivaraman, V. 2021. Hierarchical anomaly-based detection of distributed DNS attacks on enterprise networks. IEEE Transactions on Network and Service Management, 18(1), 1031-1048.
• [7] Lamdakkar, O., Ameur, I., Eleyatt, M. M., Carlier, F., Ibourek, L. A. 2024. Toward a modern secure network based on next-generation firewalls: recommendations and best practices. Procedia Computer Science, 238, 1029-1035.
• [8] Malhotra, P., Singh, Y., Anand, P., Bangotra, D. K., Singh, P. K., Hong, W. C. 2021. Internet of things: Evolution, concerns and security challenges. Sensors, 21(5).
• [9] Aslan, Ö., Aktuğ, S. S., Ozkan-Okay, M., Yilmaz, A. A., Akin, E. 2023. A comprehensive review of cyber security vulnerabilities, threats, attacks, and solutions. Electronics, 12(6).
• [10] Ahmadi, S. 2023. Next Generation AI-Based Firewalls: A Comparative Study. International Journal of Computer (IJC), 49(1), 245-262.
• [11] Ertam, F., Kaya, M. 2018. Classification of firewall log files with multiclass support vector machine. In 2018 6th International symposium on digital forensic and security (ISDFS), 22-25 Mart, Antalya, 1-4.
• [12] Al-Haijaa, Q. A., Ishtaiwia, A. 2021. Machine learning based model to identify firewall decisions to improve cyber-defense. International Journal on Advanced Science, Engineering and Information Technology, 11(4), 1688-1695.
• [13] Al-Behadili, H. N. K. 2021. Decision tree for multiclass classification of firewall access. International Journal of Intelligent Engineering and Systems, 14(3), 294-302.
• [14] Naryanto, R. F., Delimayanti, M. K. (2022, November). Machine Learning Technique for Classification of Internet Firewall Data Using RapidMiner. 2022 6th International Conference on Electrical, Telecommunication and Computer Engineering (ELTICOM), 22-23 Kasım, Medan, 155-159.
• [15] Aljabri, M., Alahmadi, A. A., Mohammad, R. M. A., Aboulnour, M., Alomari, D. M., Almotiri, S. H. 2022. Classification of firewall log data using multiclass machine learning models. Electronics, 11(12), 1851.
• [16] Rahman, M. H., Islam, T., Rana, M. M., Tasnim, R., Mona, T. R., Sakib, M. M. 2023. Machine Learning Approach on Multiclass Classification of Internet Firewall Log Files. 2023 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), 28-30 Nisan, Delhi, 358-364.
• [17] Al-Tarawneh, B. A., Bani-Salameh, H. 2023. Classification of firewall logs actions using machine learning techniques and deep neural network. AIP Proceedings, 2979(1).
• [18] Efeoğlu, E., Tuna, G. 2024. Classification of Firewall Log Files with Different Algorithms and Performance Analysis of These Algorithms. Journal of Web Engineering, 23(4), 561-593.
• [19] Lee, J. K., Hong, T., Lee, G. 2024. AI-Based Approach to Firewall Rule Refinement on High-Performance Computing Service Network. Applied Sciences, 14(11).
• [20] Haque, A. B., Islam, A. N., Mikalef, P. 2023. Explainable Artificial Intelligence (XAI) from a user perspective: A synthesis of prior literature and problematizing avenues for future research. Technological Forecasting and Social Change, 186.
• [21] Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Hussain, A. 2024. Interpreting black-box models: a review on explainable artificial intelligence. Cognitive Computation, 16(1), 45-74.
• [22] Díaz-Rodríguez, N., Del Ser, J., Coeckelbergh, M., de Prado, M. L., Herrera-Viedma, E., Herrera, F. 2023. Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation. Information Fusion, 99.
• [23] Haque, A. B., Islam, A. N., Mikalef, P. 2023. Explainable Artificial Intelligence (XAI) from a user perspective: A synthesis of prior literature and problematizing avenues for future research. Technological Forecasting and Social Change, 186.
• [24] Novelli, C., Taddeo, M., Floridi, L. 2024. Accountability in artificial intelligence: what it is and how it works. Ai & Society, 39(4), 1871-1882.
• [25] McDermid, J. A., Jia, Y., Porter, Z., Habli, I. 2021. Artificial intelligence explainability: the technical and ethical dimensions. Philosophical Transactions of the Royal Society A, 379(2207).
• [26] Hagendorff, T., Bossert, L. N., Tse, Y. F., Singer, P. 2023. Speciesist bias in AI: how AI applications perpetuate discrimination and unfair outcomes against animals. AI and Ethics, 3(3), 717-734.
• [27] Goldman, C. V., Baltaxe, M., Chakraborty, D., Arinez, J., Diaz, C. E. 2023. Interpreting learning models in manufacturing processes: towards explainable AI methods to improve trust in classifier predictions. Journal of Industrial Information Integration, 33.
• [28] Tripathi, S., Muhr, D., Brunner, M., Jodlbauer, H., Dehmer, M., Emmert-Streib, F. 2021. Ensuring the robustness and reliability of data-driven knowledge discovery models in production and manufacturing. Frontiers in artificial intelligence, 4.
• [29] Dwivedi, R., Dave, D., Naik, H., Singhal, S., Omer, R., Patel, P., Ranjan, R. 2023. Explainable AI (XAI): Core ideas, techniques, and solutions. ACM Computing Surveys, 55(9), 1-33.
• [30] Maruthi, S., Dodda, S. B., Yellu, R. R., Thuniki, P., Reddy, S. R. B. 2022. Toward a Hermeneutics of Explainability: Unraveling the Inner Workings of AI Systems. Journal of Artificial Intelligence Research and Applications, 2(2), 27-44.
• [31] El-Khawaga, G., Abu-Elkheir, M., Reichert, M. 2022. Xai in the context of predictive process monitoring: An empirical analysis framework. Algorithms, 15(6).
• [32] Feng, D. C., Wang, W. J., Mangalathu, S., Taciroglu, E. 2021. Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls. Journal of Structural Engineering, 147(11).
• [33] Sahakyan, M., Aung, Z., Rahwan, T. 2021. Explainable artificial intelligence for tabular data: A survey. IEEE Access, 9, 135392-135422.
• [34] Sim, T., Choi, S., Kim, Y., Youn, S. H., Jang, D. J., Lee, S., Chun, C. J. 2022. eXplainable AI (XAI)-based input variable selection methodology for forecasting energy consumption. Electronics, 11(18).
• [35] Tunguz, B. 2021. Internet Firewall Data Set. https://www.kaggle.com/datasets/tunguz/internet-firewall- data-set/data (Erişim Tarihi: 01.09.2024).
• [36] Mosavi, A., Sajedi Hosseini, F., Choubin, B., Goodarzi, M., Dineva, A. A., Rafiei Sardooi, E. 2021. Ensemble boosting and bagging based machine learning models for groundwater potential prediction. Water Resources Management, 35, 23-37.
• [37] Aria, M., Cuccurullo, C., Gnasso, A. 2021. A comparison among interpretative proposals for Random Forests. Machine Learning with Applications, 6.
• [38] Subbiah, S., Anbananthen, K. S. M., Thangaraj, S., Kannan, S., Chelliah, D. 2022. Intrusion detection technique in wireless sensor network using grid search random forest with Boruta feature selection algorithm. Journal of Communications and Networks, 24(2), 264-273.
• [39] Zhang, S., Li, J., Li, Y. 2022. Reachable distance function for KNN classification. IEEE Transactions on Knowledge and Data Engineering, 35(7), 7382-7396.
• [40] Dong, Y., Ma, X., Fu, T. 2021. Electrical load forecasting: A deep learning approach based on K-nearest neighbors. Applied Soft Computing, 99.
• [41] Uddin, S., Haque, I., Lu, H., Moni, M. A., Gide, E. 2022. Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction. Scientific Reports, 12(1).
• [42] Wisanwanichthan, T., Thammawichai, M. 2021. A double-layered hybrid approach for network intrusion detection system using combined naive bayes and SVM. Ieee Access, 9, 138432-138450.
• [43] Ke, T., Ge, X., Yin, F., Zhang, L., Zheng, Y., Zhang, C., Wang, W. 2024. A general maximal margin hyper-sphere SVM for multi-class classification. Expert Systems with Applications, 237, 121647.
• [44] Anyanwu, G. O., Nwakanma, C. I., Lee, J. M., Kim, D. S. 2022. Optimization of RBF-SVM kernel using grid search algorithm for DDoS attack detection in SDN-based VANET. IEEE Internet of Things Journal, 10(10), 8477- 8490.
• [45] Khalifa, R. M., Yacout, S., Bassetto, S. 2021. Developing machine-learning regression model with Logical Analysis of Data (LAD). Computers & Industrial Engineering, 151.
• [46] Huang, K., Zhang, H. 2022. Classification and regression machine learning models for predicting aerobic ready and inherent biodegradation of organic chemicals in water. Environmental Science & Technology, 56(17), 12755-12764.
• [47] Theissler, A., Thomas, M., Burch, M., Gerschner, F. 2022. ConfusionVis: Comparative evaluation and selection of multi-class classifiers based on confusion matrices. Knowledge-Based Systems, 247.
• [48] Kiangala, S. K., Wang, Z. 2021. An effective adaptive customization framework for small manufacturing plants using extreme gradient boosting-XGBoost and random forest ensemble learning algorithms in an Industry 4.0 environment. Machine Learning with Applications, 4.
• [49] Mohiuddin, G., Lin, Z., Zheng, J., Wu, J., Li, W., Fang, Y., Zeng, X. 2023. Intrusion detection using hybridized meta-heuristic techniques with Weighted XGBoost Classifier. Expert Systems with Applications, 232.
• [50] Hajihosseinlou, M., Maghsoudi, A., Ghezelbash, R. 2024. Regularization in machine learning models for MVT Pb-Zn prospectivity mapping: applying lasso and elastic-net algorithms. Earth Science Informatics, 1-15.
• [51] Vujović, Ž. 2021. Classification model evaluation metrics. International Journal of Advanced Computer Science and Applications, 12(6), 599-606.
• [52] Mubarak, A. A., Cao, H., Hezam, I. M. 2021. Deep analytic model for student dropout prediction in massive open online courses. Computers & Electrical Engineering, 93.
• [53] Lee, W., Seo, K. 2022. Downsampling for binary classification with a highly imbalanced dataset using active learning. Big Data Research, 28.
• [54] Agarwal, N., Tayal, D. K. 2022. FFT based ensembled model to predict ranks of higher educational institutions. Multimedia Tools and Applications, 81(23), 34129-34162.