Hybridising Machine Learning Algorithms for Enhanced Detection of DDoS Attacks
DOI:
https://doi.org/10.67887/PD2601202002Keywords:
Hybrid machine learning, DDoS attack detection, network traffic analysis, decision trees, cybersecurity threat detection, support vector machine (SVM)Abstract
Introduction: This study investigates the use of hybrid machine learning models to increase the accuracy of detecting Distributed Denial of Service (DDoS) attacks in network traffic data. A DDoS attack is considered a significant cybersecurity risk, and since traditional detection techniques typically fail to detect novel patterns, better detection approaches are required.
Methodology: A novel framework was created to improve the detection results, combining several machine learning models to achieve better detection results. The framework combines Support Vector Machine (SVM) with Neural Network (NN) and AdaBoost with Decision Tree, the study also combines the Decision Tree (DT) with Random Forest (RF), Gradient Boost (GB) with Random Forest, and Naive Bayes (NB) with Decision Tree. Every hybrid model improves the classification performance by utilising the advantages of each algorithm in dealing with varying patterns and noisy inputs. The APA-DDoS benchmark dataset included network traffic parameters such as source and destination IP addresses, TCP flags and packet statistics.
Results: Experimental results showed that hybrid models beat standalone classifiers regarding detection accuracy.
Conclusion: This study showed how hybrid machine learning techniques reduce the challenges of DDoS attacks. It provided a more accurate and enhanced technique for detecting attacks in real-time dynamic network situations.
References
Nagpal B, Sharma P, Chauhan N, Panesar A. DDoS tools: classification, analysis and comparison. In: 2015 2nd International Conference on Computing for Sustainable Global Development (INDIACom); 2015 Mar 11; New Delhi, India. p. 342-6. IEEE. https://ieeexplore.ieee.org/document/7100270
Muragaa WH. A hybrid scheme for detecting and preventing single packet low-rate DDoS and flooding DDoS attacks in SDN. In: 2023 IEEE 3rd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA); 2023 May 21; Tripoli, Libya. p. 707-12. IEEE.
https://doi.org/10.1109/MI-STA57575.2023.10169712
Toker O. Performance bounds for cyberattack detectors using multiple observations. In: SoutheastCon 2022; 2022 Mar 26; Mobile, AL, USA. p. 104-9. IEEE. https://doi.org/10.1109/SoutheastCon48659.2022.9764036
Li L, Yang R. Optimal control for 2-D systems under malicious attacks. In: 2022 41st Chinese Control Conference (CCC); 2022 Jul 25; Hefei, China. p. 4245-50. IEEE. https://doi.org/10.23919/CCC55666.2022.9902182
Pandey AK, Patel Y. IoT and ML based irrigation system using KNN algorithm. In: 2022 5th International Conference on Contemporary Computing and Informatics (IC3I); 2022 Dec 14; Uttar Pradesh, India. p. 779-84. IEEE. https://doi.org/10.1109/IC3I56241.2022.10072613
Pandey AK, Adhvaryu R. ML accuracy assessment of DW transaction. In: 2022 5th International Conference on Contemporary Computing and Informatics (IC3I); 2022 Dec 14; Uttar Pradesh, India. p. 800-3. IEEE. https://doi.org/10.1109/IC3I56241.2022.10073031
Hossain MA, Islam MS. Enhancing DDoS attack detection with hybrid feature selection and ensemble-based classifier: a promising solution for robust cybersecurity. Measurement: Sensors 2024; 32: 101037.
https://doi.org/10.1016/j.measen.2024.101037
Tomar A, Pant B, Tripathi V, Verma KK, Mishra S. Improving QoS of cloudlet scheduling via effective particle swarm model. In: Singh A, Gupta P, editors. Machine Learning, Advances in Computing, Renewable Energy and Communication. Singapore: Springer; 2021. p. 137-50. https://doi.org/10.1007/978-981-16-2354-7_13
Sanmorino A, Marnisah L, Di Kesuma H. Detection of DDoS attacks using fine-tuned multi-layer perceptron models. Eng Technol Appl Sci Res 2024 ;14(5): 16444-9. https://doi.org/10.48084/etasr.8362
Verma KK, Singh BM, Dixit A. A review of supervised and unsupervised machine learning techniques for suspicious behavior recognition in intelligent surveillance system. Int J Inf Technol 2022; 14(1): 397-410.
https://doi.org/10.1007/s41870-019-00364-0
Tay WY, Chin S, Chong YL. DDoS attack detection with machine learning. J Inform Web Eng 2024; 3(3):190-207. https://doi.org/10.33093/jiwe.2024.3.3.12
Elubeyd H, Yiltas-Kaplan D. Hybrid deep learning approach for automatic DoS/DDoS attacks detection in software-defined networks. Appl Sci 2023;13(6):3828. https://doi.org/10.3390/app13063828
Roopesh M, Nishat N, Rasetti S, Rahaman MA. A review of machine learning and feature selection techniques for cybersecurity attack detection with a focus on DDoS attacks. Acad J Sci Technol Eng Math Educ 2024; 4(3): 178-94. https://www.researchgate.net/publication/384249930_A_REVIEW_OF_MACHINE_LEARNING_AND_FEATURE_SELECTION_TECHNIQUES_FOR_CYBERSECURITY_ATTACK_DETECTION_WITH_A_FOCUS_ON_DDOS_ATTACKS
Kanthimathi S, Venkatraman S, Jayasankar KS, Jiljith TP, Jashwanth R. A Novel self-attention-enabled weighted ensemble-based convolutional neural network framework for distributed denial of service attack classification. IEEE Access. 2024 Oct 11. https://doi.org/10.48550/arXiv.2409.00810
Shaikh J, Butt YA, Naqvi HF. Effective intrusion detection system using deep learning for DDoS attacks. Asian Bull Big Data Manag 2024;4(1): 168-183. https://doi.org/10.62019/abbdm.v4i1.113
Musa MO, Odokuma EE. A framework for the detection of distributed denial of service attacks on network logs using ML and DL classifiers. Sci Afr 2023; 22(3): 153-64. https://doi.org/10.4314/sa.v22i3.14
Das P, Singh M, Verma KK. Blockchain-enabled deep learning approach to improve healthcare system. J Multimed Inf Syst 2024; 11(1): 9-16. https://doi.org/10.33851/JMIS.2024.11.1.9
Zahid M, Bharati TS. Enhancing cybersecurity in IoT systems: a hybrid deep learning approach for real-time attack detection. Discov Internet Things 2025; 5(1): 73. https://doi.org/10.1007/s43926-025-00156-y
Ain NU, Sardaraz M, Tahir M, Abo Elsoud MW, Alourani A. Securing IoT networks against DDoS attacks: a hybrid deep learning approach. Sensors 2025;25(5):1346. https://doi.org/10.3390/s25051346
Mahdi ZS, Zaki RM, Alzubaidi L. Advanced hybrid techniques for cyberattack detection and defense in IoT networks. Secur Privacy. 2025 ;8(2): e471. https://doi.org/10.1002/spy2.471
Sewaiwar P, Verma KK. Comparative study of various decision tree classification algorithms using WEKA. Int J Emerg Res Manag Technol. 2015; 4:2278-9359. https://www.semanticscholar.org/paper/Comparative-Study-of-Various-Decision-Tree-Using-Sewaiwar-Verma/7fd7b824fa44053551eb8f51a92a0bc590abe984
Hussain F, Hussain R, Hassan SA, Hossain E. Machine learning in IoT security: current solutions and future challenges. IEEE Commun Surv Tutorials 2020; 22(3): 1686-721. https://doi.org/10.1109/COMST.2020.2986444
Koroniotis N, Moustafa N, Sitnikova E, Turnbull B. Towards the development of realistic botnet dataset in the Internet of Things for network forensic analytics: Bot-IoT dataset. Future Gener Comput Syst 2019; 100:779-96.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mandeep Kaur (Author) and Kamal Kant Verma (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.