Call for Paper - Upcoming Issues

A Hybrid Enhanced Autoencoder and DNN Model with Adaptive Swarm Optimization for Cyberattack Detection

International Journal of Electronics and Communication Engineering
© 2026 by SSRG - IJECE Journal
Volume 13 Issue 3
Year of Publication : 2026
Authors : A. Kalaivani, R. Pugazendi
10.14445/23488549/IJECE-V13I3P121
pdf
How to Cite?

A. Kalaivani, R. Pugazendi, "A Hybrid Enhanced Autoencoder and DNN Model with Adaptive Swarm Optimization for Cyberattack Detection," SSRG International Journal of Electronics and Communication Engineering, vol. 13,  no. 3, pp. 266-281, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I3P121

Abstract:

Modern cybersecurity frameworks must include an IDS - intrusion detection system to detect and address any threats to computer networks and systems. As cyberattacks become increasingly complex, traditional intrusion detection systems often fail to perceive novel or evasive threats. To address existing IDS limitations, such as a lack of interpretability, high false positive rates, and vulnerability, this paper presents a new hybrid IDS based on Deep Neural Networks (DNN) that can automatically learn and extract features from unprocessed network data. This study is new because it combines an Enhanced Variational Autoencoder (EVAE) with a Deep Neural Network (DNN) to perform an excellent task of representing and classifying features. The proposed EVAE–DNN architecture retains high-level latent traits while decreasing redundancy and altering model parameters using Adaptive Particle Swarm Optimization, unlike previous hybrid models. This dual-stage strategy improves learning, generalization, and investigation accuracy across attack categories. The CSE-CIC-IDS2018 dataset included user activity and network traffic patterns for training and validation. OEVAEDNN_IDS outperforms other deep learning models in F1-score, recall, precision, and accuracy. Cyber threat detection and reduction are efficient, adaptive, and effective with the proposed framework.

Keywords:

Deep Learning, Intrusion detection system, Hyperparameter optimization, PSO, Variational autoencoder.

References:

[1] E. S. M. El-Alfy, and K. A. Al-Utaibi, “Learning mechanisms for anomaly-based intrusion detection: Updated review,” In 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 1273-1281), 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[2] W. Haider, G. Creech, Y. Xie, and J. Hu, “Windows-based data sets for evaluation of robustness of host-based intrusion detection systems (IDS) to zero-day and stealth attacks,” Future Internet, vol. 8, no. 3, pp. 29, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[3] M. Arun and G. Gopan, “Effects of natural light on improving the lighting and energy efficiency of buildings: toward low energy consumption and CO2 emission,” International Journal of Low-Carbon Technologies, vol. 20, pp. 1047-1056, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[4] M. M. Najafabadi, F. Villanustre, T.M. Khoshgoftaar, N. Seliya, R. Wald, and E. Muharemagic, “Deep learning applications and challenges in big data analytics,” Journal of Big Data, vol. 2, no. 1, pp. 1, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[5] W. Jo, S. Kim, C. Lee, and T. Shon, “Packet preprocessing in CNN-based network intrusion detection system,” Electronics, vol. 9, no. 7, pp. 1151, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] M. Arun, D. Barik, and S. S. Chandran, “Exploration of material recovery framework from waste–A revolutionary move towards clean environment,” Chemical Engineering Journal Advances, vol. 18, p. 100589, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] C. Ieracitano, A. Adeel, F. C. Morabito, and A. Hussain, “A novel statistical analysis and autoencoder-driven intelligent intrusion detection approach,” Neurocomputing, vol. 387, pp. 51-62, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] P. Devan, and N. Khare, “An efficient XGBoost–DNN-based classification model for network intrusion detection system,” Neural Computing and Applications, vol. 32, no. 16, pp. 12499-12514, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] M. Mohaimenuzzaman, Z. S. Abdallah, J. Kamruzzaman, and B. Srinivasan, “Effect of hyper-parameter optimization on the deep learning model proposed for distributed attack detection in Internet of Things environment,” arXiv preprint arXiv:1806.07057, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[10] J. Gu and S. Lu, “An effective intrusion detection approach using SVM with naïve Bayes feature embedding,” Computers & Security, vol. 103, pp. 102158, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] E. U. H. Qazi, M. H. Faheem, and T. Zia, “HDLNIDS: hybrid deep-learning-based network intrusion detection system,” Applied Sciences, vol. 13, no.8, pp. 4921, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] H. Kamal, and M. Mashaly, “Enhanced Hybrid Deep Learning Models-Based Anomaly Detection Method for Two-Stage Binary and Multi-Class Classification of Attacks in Intrusion Detection Systems,” Algorithms, vol. 18, no. 2, p. 69, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[13] S. A. A. A. Alsaidi, H. J. Mohammed, R. R. N. Al Ogaili, Z. A. Dashoor, A. H. Alsaeedi, D. Al-Shammary, and A. Ibaida, “HawkPhish DNN cybersecurity model: adaptive hybrid optimization and deep learning for enhanced multi-objective phishing URL detection,” International Journal of Information Technology, vol. 17, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[14] F. Alhayan, N. Alruwais, M. Alamgeer, A. M. Alashjaee, M. Abdullah, A. O. Khadidos, F. S. Alallah, and A. Alshareef, “Design of advanced intrusion detection in cybersecurity using an ensemble of deep learning models with an improved beluga whale optimization algorithm,” Alexandria Engineering Journal, vol. 121, pp. 90-102, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[15] M. Almseidin, A. Gawanmeh, M. Alzubi, J. Al-Sawwa, A. S. Mashaleh, and M. Alkasassbeh, “Hybrid deep neural network optimization with particle swarm and grey wolf algorithms for sunburst attack detection,” Computers, vol. 14, no. 3, p. 107, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[16] K. K. Gulla, P. Viswanath, S.B. Veluru, and R.R. Kumar, “Machine learning based intrusion detection techniques,” In Handbook of Computer Networks and Cyber Security: Principles and Paradigms, pp. 873-888, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Z. Chkirbene, S. Eltanbouly, M. Bashendy, N. AlNaimi, and A. Erbad, “Hybrid machine learning for network anomaly intrusion detection,” In 2020 IEEE International Conference on Informatics, IoT, and enabling technologies (ICIoT), pp. 163-170, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[18] M. Latah, and L. Toker, “An efficient flow-based multi-level hybrid intrusion detection system for software-defined networks,” CCF Transactions on Networking, vol. 3, no. 3, pp. 261-271, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Q. R. S. Fitni, and K. Ramli, “Implementation of ensemble learning and feature selection for performance improvements in anomaly based intrusion detection systems,” In 2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), pp. 118-124, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] E. Akhmetshin, D. Hudayberganov, R. Shichiyakh, S. Yellisetti, L. K. Pappala, R. D. Shukla, and S. Chandra, “An intelligent federated learning boosted cyberattack detection system for Denial-Of-Wallet attack using advanced heuristic search with multimodal approaches,” Scientific Reports, vol. 15, no. 1, pp. 14265, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Y. K. Saheed, A. A. Usman, F. D. Sukat, and M. Abdulrahman, “A novel hybrid autoencoder and modified particle swarm optimization feature selection for intrusion detection in the internet of things network,” Frontiers in Computer Science, vol. 5, pp. 997159, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] R. K. Batchu, and H. Seetha, “A hybrid detection system for DDoS attacks based on deep sparse autoencoder and light gradient boost machine,” Journal of Information & Knowledge Management, vol. 22, no. 01, pp. 2250071, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] F. Feng, X. Liu, B. Yong, R. Zhou, and Q. Zhou, “Anomaly detection in ad-hoc networks based on deep learning model: A plug and play device,” Ad hoc networks, vol. 84, pp. 82-89, 2019.
[CrossRef] [Google Scholar] [Publisher Link]