Title
Particle Swarm Optimization (PSO) based feature selection for DDOS attack detection in IOT
Authors
S.B Gopal, D. Nanthiya, Muthuraman Saminathan
Abstract
The Internet of Things (IoT) has experienced rapid expansion, which has resulted in an increased vulnerability to Distributed Denial of Service (DDoS) assaults. These attacks pose significant dangers to environments that are struggling with limited resources. When confronted with high-dimensional datasets, traditional intrusion detection systems (IDS) sometimes experience difficulties, which results in inefficient detection and a rise in the number of false alarms. In order to overcome this issue, a feature selection strategy that based on Particle Swarm Optimization (PSO) is proposed and paired with a deep learning model for efficient DDoS detection in Internet of Things (IoT) networks. A rigorous preparation of benchmark datasets, such as BoT-IoT, SDN-IoT, and KDDCUP1999, provides the foundation for the methodology. This preprocessing ensures that the data is both consistent and accurate. After that, PSO is utilized to choose the features that are most pertinent, so dramatically lowering the dimensionality of the data while maintaining the essential attack-related characteristics. In order to improve learning stability and reduce overfitting, an Artificial Neural Network (ANN) is trained using the optimized dataset. The training process includes batch normalization, dropout regularization, and early stopping. Achieving up to 96% accuracy with reduced false positives and greater generalization, the experimental results reveal significant gains in accuracy, precision, recall, and F1-score. The results demonstrate that the use of PSO-based feature selection improves detection efficiency, which makes the system appropriate for Internet of Things contexts that have limited computational resources.
Keywords
Internet of Things; Distributed Denial of Service; ANN; PSO
Full Text
References
[1] K. Al-Fawa’reh, M. Al-Fayoumi, S. Nashwan, and S. Fraihat, “Cyber threat intelligence using PCA-DNN
model to detect abnormal network behavior,” Egyptian Informatics Journal, vol. 23, no. 2, 2022.
[2] D. M. B. Lent, V. G. D. S. Ruffo, L. F. Carvalho, J. Lloret, J. J. Rodrigues, and M. L. Proença, “An
unsupervised generative adversarial network system to detect DDoS attacks in SDN,” IEEE Access, 2024.
[3] H. Bakır and Ö. Ceviz, “Empirical enhancement of intrusion detection systems: a comprehensive approach
with genetic algorithm-based hyperparameter tuning and hybrid feature selection,” Arabian Journal for Science
and Engineering, pp. 1–19, 2024.
[4] M. Bakro, R. R. Kumar, M. Husain, Z. Ashraf, A. Ali, S. I. Yaqoob, M. N. Ahmed, and N. Parveen,
“Building a cloud-IDS by hybrid bio-inspired feature selection algorithms along with random forest model,”
IEEE Access, 2024.
[5] “Advances in IoT intrusion detection: Deploying hybrid deep learning and metaheuristic algorithms for
optimal feature selection,” IIETA Journal of Information Security and Applications, 2024.
[6] A. A. Alashhab, M. S. Zahid, B. Isyaku, A. A. Elnour, W. Nagmeldin, A. Abdelmaboud, T. A. Abdullah,
and U. Maiwada, “Enhancing DDoS attack detection and mitigation in SDN using an ensemble online machine
learning model,” IEEE Access, 2024.
[7] S. Chattopadhyay, A. K. Sahoo, and S. Jasola, “An enhanced DDoS attack detection in software-defined
networks using ensemble learning,” SN Computer Science, vol. 5, no. 5, p. 580, 2024.
[8] D. Nanthiya, P. Keerthika, S. B. Gopal, S. B. Kayalvizhi, T. Raja, and R. S. Priya, “SVM,” in Proc. Int.
Conf., Nov. 2021.
[9] S. B. Gopal, C. Poongodi, M. J. A. Jude, S. Umasri, D. Sumithra, and P. Tharani, “Minimum energy
consumption objective function for RPL in Internet of Things,” International Journal of Scientific and
Technology Research, vol. 9, no. 1, pp. 1–9, 2020.
[10] M. F. Saiyed and I. Al-Anbagi, “A genetic algorithm- and t-test-based system for DDoS attack detection in
IoT networks,” IEEE Access, vol. 12, pp. 25623–25641, 2024.
[11] R. Mehssen Alhamdawee, “Optimizing feature selection for IoT intrusion detection using RFE and PSO,”
Misan Journal of Engineering Sciences, vol. 4, no. 1, pp. 236–249, 2025.
[12] Y.-E. Kim, Y.-S. Kim, and H. Kim, “Effective feature selection methods to detect IoT DDoS attack in 5G
core network,” Sensors, vol. 22, no. 10, p. 3819, 2022.
[13] S. Kumar, T. Kumar, U. Singh, O. P. Vyas, and R. Khondoker, “NFDLM: A lightweight network flowbased deep learning model for DDoS attack detection in IoT domains,” arXiv preprint arXiv:2207.10803, 2022.
[14] P. Roopak, “Multi-objective-based feature selection for DDoS attack detection in IoT networks,” IET
Networks (Early Access), 2020.
[15] R. Doshi, N. Apthorpe, and N. Feamster, “Machine learning DDoS detection for consumer internet of
things devices,” in Proc. IEEE Security and Privacy Workshops (SPW), pp. 29–35, 2018.
Particle Swarm Optimization based feature selection for DDOS attack detection
38
[16] R. Doshi, N. Apthorpe, and N. Feamster, “Machine learning DDoS detection for consumer Internet of
Things devices,” arXiv preprint arXiv:1804.04159, 2018.
[17] S. Aljawarneh, M. Aldwairi, and M. B. Yassein, “Anomaly-based intrusion detection system through
feature selection analysis and building hybrid efficient model,” Journal of Computational Science, vol. 25, pp.
152–160, 2018.
[18] S. Selvarajan, G. Srivastava, et al., “Timely detection of DDoS attacks in IoT with dimensionality
reduction,” Cluster Computing, 2024.
[19] “Towards detection of DDoS attacks in IoT with optimal features selection,” Wireless Personal
Communications, 2024.
[20] Y. Meidan, M. Bohadana, Y. Mathov, Y. Mirsky, A. Shabtai, D. Breitenbacher, and Y. Elovici, “N-baiot—
network-based detection of IoT botnet attacks using deep autoencoders,” IEEE Pervasive Computing, vol. 17,
no. 3, pp. 12–22, 2018.
[21] “Optimizing feature selection for intrusion detection: A hybrid approach using Cuckoo Search and Particle
Swarm Optimization,” International Journal of Security and its Applications (IJSSE), 2024.
[22] M. Bakro, R. R. Kumar, M. Husain, Z. Ashraf, A. Ali, S. I. Yaqoob, M. N. Ahmed, and N. Parveen,
“Building a cloud-IDS by hybrid bio-inspired feature selection algorithms along with random forest model,”
IEEE Access, vol. 12, 2024.
[23] S. Balasubramaniam, C. Vijesh Joe, T. A. Sivakumar, A. Prasanth, K. Satheesh Kumar, V. Kavitha, and R.
K. Dhanaraj, “Optimization enabled deep learning-based DDoS attack detection in cloud computing,”
International Journal of Intelligent Systems, vol. 2023, no. 1, p. 2039217, 2023.
[24] S. B. Gopal, “Mitigation of phishing URL attack in IoT using H-ANN with H-FFGWO algorithm,” KSII
Transactions on Internet & Information Systems, vol. 17, no. 7, 2023.
[25] M. Bakro, R. R. Kumar, M. Husain, Z. Ashraf, A. Ali, S. I. Yaqoob, M. N. Ahmed, and N. Parveen,
“Building a cloud-IDS by hybrid bio-inspired feature selection algorithms along with random forest model,”
IEEE Access, vol. 12, 2024.
[26] S. G. Qureshi and S. K. Shandilya, “Nature-inspired adaptive decision support system for secured
clustering in cyber networks,” Springer Nature, 2024.
[27] H. N. Mohsenabad and M. A. Tut, “Optimizing cybersecurity attack detection in computer networks: A
comparative analysis of bio-inspired optimization algorithms using the CSE-CIC-IDS2018 dataset,” Applied
Sciences, vol. 14, 2024.
[28] G. Sripriyanka and A. Mahendran, “Securing IoMT: A hybrid model for DDoS attack detection and
COVID-19 classification,” IEEE Internet of Medical Things Journal, vol. 12, 2024.
[29] P. Sangkatsanee, N. Wattanapongsakorn, and C. Charnsripinyo, “Practical real-time intrusion detection
using machine learning approaches,” Computer Communications, vol. 34, no. 18, pp. 2227–2235, 2011.
[30] P. Wuttidittachotti, “DDoS attack detection using deep learning,” IAES International Journal of Artificial
Intelligence, vol. 10, no. 1, 2021.