An Intelligent Intrusion Detection System for DDoS Attacks Using Deep Neural Networks | IJCT Volume 13 – Issue 1 | IJCT-V13I1P1
International Journal of Computer Techniques
ISSN 2394-2231
Author
D. A Aina, J.A Ayeni, F. E. Ayo, A. O. Ogunjobi
Abstract
The emergent dependence on internet-based facilities highlights the exigent need for strong network security, especially in alleviating Distributed Denial-of-Service (DDoS) outbreaks, which seriously disrupt service accessibility and cause significant financial losses. DDoS attacks devastate targeted systems with large volumes of traffic from numerous sources, resulting to downtime and performance dilapidation. Prompt recognition of such attacks remains a serious challenge in cybersecurity. Existing methods often suffer from high false positive rates and inadequate capability to detect the various and complex traffic patterns related with contemporary DDoS attacks, resulting in limited accuracy.
This research work presents an enhanced intrusion detection framework leveraging deep learning techniques for effective identification of DDoS attacks. Three architectures Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU) were used on the CICDDoS2019 dataset sourced from Kaggle. Comparative evaluation shows that the CNN model attained higher performance, exhibiting an accuracy of 99.73%, precision of 99.70%, recall of 99.85%, and F1-score of 99.77%. These outcomes reveal CNN’s ability to effectively distinguish between benign and harmful outbreaks while reducing false positives and false negatives. The outcomes validate the effectiveness of deep learning, especially CNN-based models, in exhibiting extremely accurate early exposure of DDoS outbreaks, thus improving network resilience against emerging cyber threats.
Keywords
Distributed Denial-of-Service (DDoS), Deep Learning, Intrusion Detection System (IDS), Convolutional Neural Network (CNN), Network Security, Cybersecurity
Conclusion
The study recommends that applying this new development can significantly advance the university’s cybersecurity strenght. Future work may involve tunung the model, applying it in real-world situations, and evaluating its performance in alleviating DDoS attack through different network environments. This work may serve as a benchmack for McPherson University to improve its digital security organization through state-of-the-art technique.
c. Recommendations to McPherson University ICT
The outcome of this research work depict that McPherson University ICT can take the following practical approach to improve its cybersecurity against DDoS occurrences.
i.Regular Model Updates
They must ensure a regular updates of the deep learning model using newer data. This approach will aid the model to be more active in identifying emerging DDoS outbreak patterns and adapting to variations in network performance at any period of time.
ii. Explore Hybrid Models:
They can source for Hybrid models that can combine deep learning with other techniques. Incorporating deep learning with traditional statistical techniques or rule-based systems can hypothetically widen the model’s proficiencies. This method will increase the model accuracy in identifying multifaceted DDoS outbreak patterns and reducing false positives.
d.Future Works
Looking at the future advances, the plan was to improve the efficiency and real-world application of deep learning in recognizing DDoS outbreaks, eventually consolidation cybersecurity status through different segment and situations;
i.Addressing Evolving Attack Techniques – Adversarial Learning
Adversarial learning provides a encouraging approach in other to move with the ever-changing techniques of DDoS outbreaks, This approach has to do with training deep learning models to recognize and change to new outbreak methods produce by malicious occurrences; this is done by repeatedly subjecting the
model to mimicked outbreak instances, adversarial learning make stronger the capability to develop systems that can work with multifarious and sprouting DDoS attack.
ii.Scaling and Deployment
Also, it is necessary to make sure that the DDoS recognition models would be able to efficiently weighbridge larger networks within an organizational setup. This has to do with trying the models in experimental projects and before deploying them for use in other environs. This will assist one to know how thriving they can work in changing situations and network oodles.
iii.Collaborative Defense Mechanisms – Federated Learning:
Federated learning gives a collective method to improving DDoS resistance through circulated networks. Not like the existing central approaches, federated learning enables each network connectors to individually train a Deep Learning models through their personal data; where merely there accumulated updates out of these models will be shared on the central server, protection data confidentiality. This distributed approach assists various networks to communally optimize model accuracy and compliance without degrading profound information, in so doing improving the efficiency of DDoS recognition and alleviation effect.
References
[1] I. AlSaleh, A. Al-Samawi, and L. Nissirat, “Novel machine learning approach for DDoS cloud detection: Bayesian-based CNN and data fusion enhancements,” *Sensors*, vol. 24, no. 5, p. 1418, 2024. [Online]. Available: https://doi.org/10.3390/s24051418
[2] G. C. Amaizu, C. I. Nwakanma, S. Bhardwaj, J. M. Lee, and D. S. Kim, “Composite and efficient DDoS attack detection framework for B5G networks,” *Computer Networks*, vol. 188, p. 107871, 2021. [Online]. Available: https://doi.org/10.1016/j.comnet.2021.107871
[3] M. Asad, M. Asim, T. Javed, M. O. Beg, H. Mujtaba, and S. Abbas, “DeepDetect: Detection of distributed denial of service attacks using deep learning,” *The Computer Journal*, 2019. [Online]. Available: https://doi.org/10.1093/comjnl/bxz064
[4] M. Badsha, “A beginner’s guide to understanding DDoS attacks & how to protect your site,” *Host SEO*, Jul. 4, 2019. [Online]. Available: https://blog.hostseo.com/a-beginners-guide-to-understanding-ddosattackshow-to-protect-your-site/
[5] J. Brownlee, Understand the dynamics of learning rate on deep learning neural networks. Machine Learning Mastery, 2020. [Online]. Available: https://machinelearningmastery.com/understand-the-dynamics-of-learning-rate-on-deeplearning-neural-networks/
[6] J. Brownlee, Gentle introduction to the Adam optimization algorithm for deep learning. Machine Learning Mastery, Jan. 13, 2021. [Online]. Available: https://machinelearningmastery.com/adam-optimization-algorithm-for-deep-learning/
[7] J. Brownlee, “Difference between a batch and an epoch in a neural network,” Machine Learning Mastery, Aug. 15, 2022. [Online]. Available: https://machinelearningmastery.com/difference-between-a-batch-and-an-epoch/. [Accessed: Apr. 4, 2023].Cil, A. E.,
[8] K. Yildiz and A. Buldu, “Detection of DDoS attacks with feed forward based deep neural network model,” Expert Systems with Applications, vol. 169, p. 114520, 2021. [Online]. Available: https://doi.org/10.1016/j.eswa.2020.114520
[9] K. Some, “The history, evolution and growth of deep learning,” Analytics Insight, Oct. 30, 2018. [Online]. Available: https://www.analyticsinsight.net/deep-learning/the-history-evolution-andgrowth-of-deep-learning
[10] A. Kumar, “Deep learning explained in layman’s terms,” DZone, Oct. 8, 2020. [Online]. Available: https://dzone.com/articles/deep-learning-explained-simply-in-layman-terms-dat
[11] M. Mittal, K. Kumar, and S. Behal, “Deep learning approaches for detecting DDoS attacks: A systematic review,” Soft Computing, 2022. [Online]. Available: https://doi.org/10.1007/s00500-021-06608-1
[12] M. Mittal, K. Kumar, and S. Behal, “Deep learning approaches for detecting DDoS attacks: A systematic review,” Soft Computing, vol. 27, no. 18, pp. 13039–13075, 2022. [Online]. Available: https://doi.org/10.1007/s00500-021-06608-1
[13] O. Sbai and M. El Boukhari, “Data flooding intrusion detection system for MANETs using deep learning approach,” Proceedings of the 2020 International Conference on Computing, Control, Networking, Electronics, and Embedded Systems Engineering (ICCCNEE), 2020. [Online]. Available: https://doi.org/10.1145/3419604.3419777
[14] M. Ramzan, M. Shoaib, A. Altaf, S. Arshad, F. Iqbal, N. K. Castilla, and I. Ashraf, “Distributed denial of service attack detection in network traffic using deep learning algorithm,” Sensors, vol. 23, no. 20, p. 8642, 2023. [Online]. Available: https://doi.org/10.3390/s23208642
[15] A. R. Shaaban, E. Abd-Elwanis, and M. Hussein, “DDoS attack detection and classification via convolutional neural network (CNN),” IEEE Xplore, Dec. 1, 2019. [Online]. Available: https://doi.org/10.1109/ICICIS46948.2019.9014826
[16] K. B. Virupakshar, M. Asundi, K. Channal, P. Shettar, S. Patil, and D. G. Narayan, “Distributed denial of service (DDoS) attacks detection system for OpenStack-based private cloud,” Procedia Computer Science, vol. 167, pp. 2297–2307, 2020. [Online]. Available: https://doi.org/10.1016/j.procs.2020.03.282
[17] K. W. Wan, C. H. Wong, H. F. Ip, D. Fan, P. L. Yuen, H. Y. Fong, and M. Ying, “Evaluation of the performance of traditional machine learning algorithms, convolutional neural network and Auto ML Vision in ultrasound breast lesions classification: a comparative study,” Quantitative Imaging in Medicine and Surgery, vol. 11, no. 4, p. 1381, 2021.
[18] A. Wilson and M. R. Anwar, “The future of adaptive machine learning algorithms in high-dimensional data processing,” International Transactions on Artificial Intelligence, vol. 3, no. 1, pp. 97–107, 2024. [19] C. Muraleedharan and B. Janet, “Deep learning-based classification of HTTP slow DoS attacks using flow data,” Procedia Computer Science, vol. 171, pp. 1126–1135, 2
How to Cite This Paper
D. A Aina, J.A Ayeni, F. E. Ayo, A. O. Ogunjobi (2025). An Intelligent Intrusion Detection System for DDoS Attacks Using Deep Neural Networks. International Journal of Computer Techniques, 12(6). ISSN: 2394-2231.
Related Posts:
