DDoSGedik30K: DDoS Saldırı Tespiti için Benzersiz Bir Veri Seti ve Gelişmiş Derin Öğrenme Teknikleri

Yıl 2025, Cilt: 3 Sayı: 2, 86 - 102, 28.09.2025

Şenay Kocakoyun Aydoğan , Turgut Pura , Zeki Çıplak , Anıl Yıldız

https://doi.org/10.61150/ijonfest.2025030201

Öz

Ağ teknolojilerindeki hızlı gelişmeler ve ağlar üzerinde aktarılan verilerin miktarı ve kapsamı her geçen gün artmaktadır. Bu duruma bağlı olarak siber tehdit ve saldırıların yoğunluğu ve karmaşıklığı da genişlemektedir. Özellikle DDoS (Distributed Denial of Service) saldırıları, ağ ve sistem güvenliğini tehdit eden en yaygın ve yıkıcı siber saldırı türlerinden biri olarak dikkat çekmektedir. Bu çalışma, günümüzde giderek artan DDoS saldırılarına karşı etkili bir tespit mekanizması geliştirmek amacıyla derin öğrenme tekniklerinin kullanımını incelemektedir. Bu amaçla, gerçek dünya saldırı senaryolarını içeren DDoSGedik30K adlı bir veri seti oluşturulmuştur. Bu veri seti kullanılarak, Feedforward Neural Network (FFNN) ve Long Short-Term Memory (LSTM) derin öğrenme mimarilerinde toplam 12 model geliştirilmiştir. Geliştirilen tüm modellerin %99.9 doğruluk oranına ulaşması, önerilen veri setinin DDoS saldırılarını tespit etmede son derece etkili olduğunu ispat etmiştir. Çalışmada önerilen veri seti ve DDoS saldırı tespiti için optimize edilmiş derin öğrenme modelleri, literatüre önemli bir katkı sağlamaktadır ve gelecekteki siber güvenlik araştırmaları için yol gösterici olabilecek bulgular sunmaktadır.

Anahtar Kelimeler

DDoS Algılama , Derin Öğrenme , DDoS Veri Seti , DDoSGedik30K , DDoS Analizi

Proje Numarası

GDK202207-32

DDoSGedik30K: A Unique Dataset and Advanced Deep Learning Techniques for DDoS Attack Detection

Öz

The rapid advancements in network technologies, along with the increasing volume and scope of data transmitted over networks, have led to a rise in both the intensity and complexity of cyber threats and attacks. One of the most prominent and destructive types of cyberattacks threatening network and system security is the Distributed Denial of Service (DDoS) attack. This study examines the use of deep learning techniques to develop an effective detection mechanism against the growing number of DDoS attacks today. For this purpose, a dataset called DDoSGedik30K, which includes real-world attack scenarios, was created. Using this dataset, a total of 12 models were developed based on Feedforward Neural Network (FFNN) and Long Short-Term Memory (LSTM) deep learning architectures. The fact that all models achieved a 99.9% accuracy rate proves that the proposed dataset is highly effective in detecting DDoS attacks. The dataset and the optimized deep learning models for DDoS attack detection proposed in this study provide a significant contribution to the literature and offer findings that could guide future cybersecurity research.

Anahtar Kelimeler

DDoS Detection , Deep Learning , DDoS Dataset , DDoSGedik30K , DDoS Analysis.

Etik Beyan

This work was supported by Scientific Research Projects Coordination Unit of Istanbul Gedik University, Project number “GDK202207-32”.

Destekleyen Kurum

Istanbul Gedik University

Proje Numarası

GDK202207-32

Kaynakça

• [1] Aamir, M., Zaidi, S.M.A., 2019. DDoS attack detection with feature engineering and machine learning: the framework and performance evaluation. International Journal of Information Security, 18: p. 761-785.
• [2] Büyüktanır, B., et al. 2025. DDoS_FL: Federated Learning Architecture Approach against DDoS Attack. Pamukkale University Journal of Engineering Sciences, 31(6), 0-0.
• [3] Carl, G., et al., 2006. Denial-of-service attack-detection techniques. IEEE Internet computing, 10(1): p. 82-89.
• [4] Anli, Y.A., et al., 2024. DDoS detection in electric vehicle charging stations: A deep learning perspective via CICEV2023 dataset. Internet of Things, 28: p. 101343.
• [5] Mitrokotsa, A. Douligeris, C., 2007. Denial-of-service attacks. Network Security: Current Status and Future Directions, p. 117-134.
• [6] Özocak, G., 2012. DDoS Saldırısı ve Failin Cezai Sorumluluğu. Bilişim, 28: p. 23.
• [7] Feily, M., Shahrestani, A., Ramadass, S., 2009. A survey of botnet and botnet detection. in 2009 Third International Conference on Emerging Security Information, Systems and Technologies. IEEE.
• [8] Dayanandam, G., et al., 2019. DDoS attacks—analysis and prevention. in Innovations in Computer Science and Engineering: Proceedings of the Fifth ICICSE 2017. Springer.
• [9] Zhu, Z., et al., 2008. Botnet research survey. in 2008 32nd Annual IEEE International Computer Software and Applications Conference. IEEE.
• [10] Zhang, L., et al., 2011. A survey on latest botnet attack and defense. in 2011IEEE 10th International Conference on Trust, Security and Privacy in Computing and Communications. IEEE.
• [11] Efe, A., 2021. Yapay Zekâ Odaklı Siber Risk ve Güvenlik Yönetimi. Uluslararası Yönetim Bilişim Sistemleri ve Bilgisayar Bilimleri Dergisi, 5(2): p. 144-165.
• [12] Mittal, M., K. Kumar, S. Behal, 2023. Deep learning approaches for detecting DDoS attacks: A systematic review. Soft computing, 27(18): p. 13039-13075.
• [13] Atasever, S., Özçelık İ., Sağiroğlu, Ş. 2020. An Overview of Machine Learning Based Approaches in DDoS Detection. in 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE.
• [14] Erhan, D., Anarım, E., 2020. Istatistiksel Yöntemler Ile DDoS Saldırı Tespiti DDoS Detection Using Statistical Methods. in 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE.
• [15] Asarkaya, S., et al., 2021. DDOS SALDIRILARININ MAKİNE ÖĞRENİMİ ALGORİTMALARIYLA TESPİTİ. Tasarım Mimarlık ve Mühendislik Dergisi, 1(3): p. 221-232.
• [16] Sharif, D.M., Beitollahi, H., 2023.Detection of application-layer DDoS attacks using machine learning and genetic algorithms. Computers & Security, 135: p. 103511.
• [17] Stiawan, D., et al., 2020. CICIDS-2017 dataset feature analysis with information gain for anomaly detection. IEEE Access, 8: p. 132911-132921.
• [18] Priya Devi, Johnson Singh, A. K., 2021. A machine learning approach to intrusion detection system using UNSW-NB-15 and CICDDoS2019 datasets. in Smart Computing Techniques and Applications: Proceedings of the Fourth International Conference on Smart Computing and Informatics, Volume 1. Springer.
• [19] Ahmed, S., et al., 2023. Effective and efficient DDoS attack detection using deep learning algorithm, multi-layer perceptron. Future Internet, 15(2): p. 76.
• [20] Sharif, D.M., Beitollahi, H., Fazeli, M., 2023. Detection of application-layer DDoS attacks produced by various freely accessible toolkits using machine learning. IEEE Access, 11: p. 51810-51819.
• [21] Kareem, M.K., et al., 2023. Efficient model for detecting application layer distributed denial of service attacks. Bulletin of Electrical Engineering and Informatics, 12(1): p. 441-450.
• [22] Salama, A.M., Mohamed, M.A., AbdElhalim, E., 2024. Enhancing Network Security in IoT Applications through DDoS Attack Detection Using ML. Mansoura Engineering Journal, 49(3): p. 10.
• [23] Hussein, T., 2024. Deep Learning-based DDoS Detection in Network Traffic Data. International journal of electrical and computer engineering systems, 15(5): p.407-414.
• [24] Manaa, M.E., et al., 2024. DDoS attacks detection based on machine learning algorithms in IoT environments. Inteligencia Artificial, 27(74): p. 152-165.
• [25] Najar, A.A., et al., 2024. A novel CNN‐based approach for detection and classification of DDoS attacks. Concurrency and Computation: Practice and Experience, 36(19): p. e8157.
• [26] Zekri, M., et al. DDoS attack detection using machine learning techniques in cloud computing environments. in 2017 3rd international conference of cloud computing technologies and applications (CloudTech). 2017. IEEE.
• [27] Ahda, A., et al., 2023.Information security implementation of DDoS attack using hping3 tools. JComce-Journal of Computer Science, 1(4).
• [28] Koziol, J., 2003. Intrusion detection with Snort. Sams Publishing.
• [29] Liao, H.-J., et al., 2013. Intrusion detection system: A comprehensive review. Journal of Network and Computer Applications, 36(1): p. 16-24.
• [30] Yuan, X., Li, C. X. Li., 2017. DeepDefense: identifying DDoS attack via deep learning. in 2017 IEEE international conference on smart computing (SMARTCOMP). IEEE.
• [31] Dalalana Bertoglio, D. Zorzo, A.F., 2017. Overview and open issues on penetration test. Journal of the Brazilian Computer Society, 23: p. 1-16.
• [32] Kim, Y.-E., Y.-S. Kim, and H. Kim, 2022. Effective feature selection methods to detect IoT DDoS attack in 5G core network. Sensors,. 22(10): p. 3819.
• [33] Kumari, P., et al., 2024. Towards Detection of DDoS Attacks in IoT with Optimal Features Selection. Wireless Personal Communications, p. 1-26.
• [34] Lyu, M.R., Lau, L.K., 2000. Firewall security: Policies, testing and performance evaluation. in Proceedings 24th Annual International Computer Software and Applications Conference. COMPSAC2000. IEEE.
• [35] Khraisat, A., Alazab, A. 2021. A critical review of intrusion detection systems in the internet of things: techniques, deployment strategy, validation strategy, attacks, public datasets and challenges. Cybersecurity, 4: p. 1-27.
• [36] Fabbri, R., Volpe, F., 2013. Getting started with fortigate. Packt Publishing Ltd.
• [37] Towidjojo, R., 2023. Mikrotik Kung Fu: Kitab 4. Jasakom.
• [38] Ali, B.H., et al. 2022. Ddos detection using active and idle features of revised cicflowmeter and statistical approaches. in 2022 4th International Conference on Advanced Science and Engineering (ICOASE). IEEE.
• [39] Lamping, U., E. Warnicke, 2004. Wireshark user's guide. Interface, 4(6): p. 1.
• [40] Patro, S. and K.K. Sahu, Normalization: A preprocessing stage. arXiv preprint arXiv:1503.06462, 2015.
• [41] Cabello-Solorzano, K., et al., 2023. The impact of data normalization on the accuracy of machine learning algorithms: a comparative analysis. in International Conference on Soft Computing Models in Industrial and Environmental Applications. Springer.
• [42] Demircioğlu, A., 2024. The effect of feature normalization methods in radiomics. Insights into Imaging, 15(1): p. 2.
• [43] Bebis, G., Georgiopoulos, M.,1994. Feed-forward neural networks. Ieee Potentials, 13(4): p. 27-31.
• [44] Fine, T.L., 2006. Feedforward neural network methodology. Springer Science & Business Media.
• [45] Glorot, X., Bengio, Y., 2010. Understanding the difficulty of training deep feedforward neural networks. in Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings.
• [46] Graves, A., Graves, A., 2012. Long short-term memory. Supervised sequence labelling with recurrent neural networks, p. 37-45.
• [47] Hochreiter, S., Schmidhuber, J.,1997. Long short-term memory. Neural computation, 9(8), p. 1735-1780.
• [48] Medsker, L.R., Jain, L., 2001. Recurrent neural networks. Design and Applications, 5(64-67): p. 2.
• [49] Medsker, L., Jain, L.C., 1999. Recurrent neural networks: design and applications. CRC press.
• [50] Agarap, A.F., 2018. Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375.
• [51] Hara, K., Saito, D., Shouno, H., 2015. Analysis of function of rectified linear unit used in deep learning. in 2015 international joint conference on neural networks (IJCNN). IEEE.
• [52] Hochreiter, S., 1998. The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6(02): p. 107-116.
• [53] Srivastava, N., 2013. Improving neural networks with dropout. University of Toronto, 182(566), p. 7.
• [54] Yin, X., et al., 2003. A flexible sigmoid function of determinate growth. Annals of botany, 91(3): p. 361-371.
• [55] Abadi, M., et al., 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467.
• [56] Ketkar, N., Ketkar, N., 2017. Introduction to keras. Deep learning with python: a hands-on introduction, p. 97-111.
• [57] Bressert, E., 2012 .SciPy and NumPy: an overview for developers.
• [58] Unpingco, J., 2021. Pandas, in Python Programming for Data Analysis. Springer. p. 127-156.
• [59] Kramer, O., Kramer, O., 2016. Scikit-learn. Machine learning for evolution strategies, p. 45-53.
• [60] Jais, I.K.M., Ismail, A.R., Nisa, S.Q., 2019. Adam optimization algorithm for wide and deep neural network. Knowl. Eng. Data Sci., 2(1), p. 41-46.
• [61] Reyad, M., Sarhan, A.M., Arafa, M., 2023. A modified Adam algorithm for deep neural network optimization. Neural Computing and Applications, 35(23), p. 17095-17112.
• [62] Jentzen, A., et al., 2021.Strong error analysis for stochastic gradient descent optimization algorithms. IMA Journal of Numerical Analysis, 41(1): p. 455-492.
• [63] Bottou, L., 1991. Stochastic gradient learning in neural networks. Proceedings of Neuro-Nımes,. 91(8), p. 12.
• [64] Lazaris, A., Prasanna, V.K., 2019.An LSTM Framework For Modeling Network Traffic. in 2019 IFIP/IEEE Symposium on Integrated Network and Service Management (IM).
• [65] Usmani, M., et al. 2022. Predicting ARP spoofing with Machine Learning. in 2022 International Conference on Emerging Trends in Smart Technologies (ICETST).
• [66] Fawcett, T. (2006). An introduction to ROC analysis. Pattern recognition letters, 27(8), 861-874.