Hybrid Deep Learning Enhanced with A Novel Feature Extraction Technique for Detection and Mitigation of Cyber Threats

References

[1] Abdulrahman, L. M., Ahmed, S. H., Rashid, Z. N., Jghef, Y. S., Ghazi, T. M., & Jader, U. H. (2023). Web phishing detection using web crawling, cloud infrastructure, and a deep learning framework. Journal of Applied Science and Technology Trends, 4(1), 54–71.

[2] Ahmed, N., Ngadi, A. B., Sharif, J. M., Hussain, S., Uddin, M., Rathore, M. S., Iqbal, J., Abdelhaq, M., Alsaqour, R., Ullah, S. S., & others. (2022). Network threat detection using machine/deep learning in SDN-based platforms: A comprehensive analysis of state-of-the-art solutions, discussion, challenges, and future research direction. Sensors, 22, 7896. https://doi.org/10.3390/s22207896

[3] Alkhalidi, N., & Yaseen, F. (2021). FDPHI: Fast deep packet header inspection for data traffic classification and management. International Journal of Intelligent Engineering and Systems, 14(4). https://doi.org/10.22266/ijies2021.0831.33

[4] Almousa, M., Zhang, T., Sarrafzadeh, A., & Anwar, M. (2022). Phishing website detection: How effective are deep learning-based models and hyperparameter optimization? Security and Privacy, 5(6), e256.

[5] Çelebi, M., Özbilen, A., &Yavanoğlu, U. (2023). A comprehensive survey on deep packet inspection for advanced network traffic analysis: Issues and challenges. NÖHÜ Journal of Engineering Sciences, 12(1), 001–029. https://doi.org/10.28948/ngmuh.1184020

[6] CHIDI, E. U., UDANOR, C. N., & ANOLIEFO, E. (2024). Exploring the Depths of Visual Understanding: A Comprehensive Review on Real-Time Object of Interest Detection Techniques. Preprints. https://doi.org/10.20944/preprints202402.0583.v1

[7] Ebere Uzoka Chidi, E Anoliefo, C Udanor, AT Chijindu, LO Nwobodo (2025)” A Blind navigation guide model for obstacle avoidance using distance vision estimation based YOLO-V8n; Journal of the Nigerian Society of Physical Sciences, 2292-229; https://doi.org/10.46481/jnsps.2025.2292

[8] Elberri, M. A., Tokeşer, Ü., Rahebi, J., Akin, E., & Yilmaz, M. (2024). A cyber defense system against phishing attacks with deep learning game theory and LSTM-CNN with African vulture optimization algorithm (AVOA). International Journal of Information Security, 23, 2583–2606. https://doi.org/10.1007/s10207-024-00851-x

[9] Ferguson-Walter, K., Fugate, S., Mauger, J., & Major, M. (2019). Game theory for adaptive defensive cyber deception. In Proceedings of the 6th Annual Symposium on Hot Topics in the Science of Security (pp. 1–8).

[10] Ghosh, A., & Senthilrajan, A. (2019). An approach for detecting spear phishing using deep packet inspection and deep flow inspection. In Proceedings of the 5th International Conference on Cyber Security & Privacy (ICCS).

[11] Guo, Y. (2023). A review of machine learning-based zero-day attack detection: Challenges and future directions. Computers and Communication, 198, 175–185.

[12] Kim, J., Camtepe, S., Baek, J., Susilo, W., Pieprzyk, J., & Nepal, S. (2020). P2DPI: Practical and privacy-preserving deep packet inspection. University of Wollongong, Australia CSIRO Data61, Australia.

[13] Lee, S., Kareem, A. B., & Hur, J. W. (2024). A comparative study of deep-learning autoencoders (DLAEs) for vibration anomaly detection in manufacturing equipment. Electronics, 13, 1700. https://doi.org/10.3390/electronics13091700

[14] Li, C., Guo, Y., & Wang, X. (2022). Towards privacy-preserving dynamic deep packet inspection over outsourced middleboxes. High-Confidence Computing, 2, 100033. https://doi.org/10.1016/j.hcc.2021.100033

[15] Parra, G., Rad, P., & Choo, K. (2019). Implementation of deep packet inspection in smart grids and industrial Internet of Things: Challenges and opportunities. Journal of Network and Computer Applications, 32–46. https://doi.org/10.1016/j.jnca.2019.02.022

[16] Pawlick, J., Colbert, E., & Zhu, Q. (2019). A game-theoretic taxonomy and survey of defensive deception for cybersecurity and privacy. ACM Computing Surveys (CSUR), 52(4), 1–28.

[17] Piazza, N. (2020). A study on the effectiveness of machine learning techniques to detect and prevent zero-day cyberattacks [Doctoral dissertation, ProQuest LLC].

[18] Ren, H., Li, H., Liu, D., Xu, G., Cheng, N., & Shen, X. (2020). Privacy-preserving efficient verifiable deep packet inspection for cloud-assisted middlebox. IEEE Transactions on Cloud Computing. https://doi.org/10.1109/TCC.2020.2991167

[19] Rouamel, M., Bourahala, F., Guelton, K., Bouzoualegh, S., & Arcese, L. (2022). Fuzzy weighted memory event-triggered control for networked control systems subject to deception attacks. IFAC PapersOnline, 55(15), 45–51.

[20] Sharma, S. R., Singh, B., & Kaur, M. (2020). Improving the classification of phishing websites using a hybrid algorithm. Computational Intelligence, 38(2), 667–689.

[21] Sochima V.E. Asogwa T.C., Lois O.N. Onuigbo C.M., Frank E.O., Ozor G.O., Ebere U.C. (2025)”; Comparing multi-control algorithms for complex nonlinear system: An embedded programmable logic control applications; DOI: http://doi.org/10.11591/ijpeds.v16.i1.pp212-224

[22] Sun, Y., Chong, N., & Ochiai, H. (2020). Federated phish bowl: LSTM-based decentralized phishing email detection. In 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 20–25).

@article{1709699,
      author = {Asogwa T. C., Ezeh Ebere M.},
      title = {Hybrid Deep Learning Enhanced with A Novel Feature Extraction Technique for Detection and Mitigation of Cyber Threats},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {1},
      pages = {841-850},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1709699.pdf},
      abstract = {This paper proposes a new real-time feature detection and mitigation framework of cyber threats that will be based on hybrid deep learning technique. The system proposed uses Convolutional Neural Networks (CNN) as the part that extracts the spatial features and Autoencoders (AE) as the part that reduces the number of dimensions and detect anomalies resulting in a CNN enhanced with AE architecture that is optimized and can be used in cyber security applications. One of the main novelties of the system is the usage of a feature extraction method based on cross-correlation and it manages to dynamically select the most appropriate network traffic features by assessing the inter-feature relationships over time which provides the model with flexibility in response to a changing trend of threat and discards duplicating or noise data. The system used Python with TensorFlow and Keras to implement deep learning and tested on a virtualized platform with both synthetic. Evaluation terms showed good results, the training accuracy was 89.23%, validation accuracy was 86.74%, and minimal classification loss. The findings have shown that the CNN and AE in combination with feature extraction of the cross-correlation method has great preference to the accuracy and efficiency of network threat detection systems. The framework provides flexible and scalable real-time cybersecurity defence that can be used to reduce false positives and at the same time guarantee prompt mitigating effects.},
      keywords = {Cybersecurity; Convolutional Neural Network (CNN); Autoencoder (AE); Cross-Correlation Feature Extraction; Real-Time Threat Mitigation},
      month = {July},
  }