Ensemble of 1D-CNN and LightGBM for Encrypted Traffic Differentiation and Attack Detection
Keywords:
Encrypted Form of Traffic Differentiation, Attack Identification, 1D-CNN Mod, Light type GBM, Ensemble Based Learning, Supervisor Learning, Gradient Type Boosting, Threat Identification, Attacks Traffic AnalysisAbstract
Encrypted network data traffic has turned into a double-edged model , protecting user privacy while at the same time masking the malicious behavior from conventional detection systems. To overcome this issue, the system in this proposal comes up with an ensemble type model that combines one- dimensional Convolutional Neural infrastructure (1D- CNN) with Light Gradient Boosting type Machine (LightGBM) in order to effective way of classifies encrypted traffic and detect attacks. The 1D-CNN module is an effective related feature absorbs that learns to automatically capture complex temporal and spatial data patterns hidden within raw unseen traffic streams without any manual feature process. The deep representations will then refined by the LightGBM type model, which is particularly strong in efficient differentiation with the use of gradient-depending decision trees and capable of dealing with complicated decision boundaries with higher scalability. The advantage of deep learning's representational power and gradient boosting's strong decision-maker ability provides an extensive detection process that is capable of differentiation of benign from malicious data traffic in the presence of encryption. By utilizing both techniques together in a complementary type, the framework improves the reliability of detection, lowers false alarms, and improves adaptability to changing attack schemas, thus giving a feasible and smart solution for recent cybersecurity systems.
References
[1] Baskar, K., Muthuraj, S., Sangeetha, S., Vengatesan, K., Aishwarya, D., & Yuvaraj, P. S. (2022, March). Framework for implementation of smart driver assistance system using augmented reality. In International Conference on Big data and Cloud Computing (pp. 231- 248). Singapore: Springer Nature Singapore.
[2] Hassn, B. M., Alomari, E. S., Alrubaye, J. S., & Hassen, O. A. (2025). Adversarially Robust 1D-CNN for Malicious Traffic Detection in Network Security Applications. Journal of Cybersecurity & Information Management, 16(1).
[3] Battah, M. H., & AL-Saedi, K. H. (2025, April). Anomaly detection in network traffic using 1D CNNs: Insights from explainable AI techniques. In AIP Conference Proceedings (Vol. 3282, No. 1, p. 020008). AIP Publishing LLC.
[4] Baskar, K., Venkatesan, G. P., & Sangeetha, S. (2020). A Survey of Workload Management Difficulties in the Public Cloud. In Intelligent Computing in Engineering: Select Proceedings of RICE 2019 (pp. 491-499). Singapore: Springer Singapore.
[5] Sharma, A., & Habibi Lashkari, A. (2025). Hybrid attention-enhanced explainable model for encrypted traffic detection and classification: A. Sharma et al. International Journal of Information Security, 24(3), 144.
[6] El-Gayar, M. M., Alrslani, F. A., & El-Sappagh, S. (2024). Smart collaborative intrusion detection system for Securing vehicular networks using ensemble machine learning model. Information, 15(10), 583.
[7] Tanmay Kasbe and Ravi Singh Pippal, “Design and Implementation of Fuzzy Expert System for Dengue Diagnosis”, In Springer International Conference on Advanced Computing, Networking and Informatics (ICANI-2018), Medi-Caps University, Indore, 22nd To 24th Feb 2018.
[8] Lakshmi. J, Rajeshwari. J, Review on Safe Reversible Image Data Hiding across an Enciphered Environment, Proceedings of the IEEE 2017 International Conference on Computing Methodologies and Communication, (ICCMC), 978-1-5090- 4890-8/17/$31.00, 2017 IEEE
[9] Darnal, K. (2024). A comparative analysis of machine learning algorithms in network-based intrusion detection systems for detecting advanced persistent threats to enhance cybersecurity.
[10] Liu, Y. (2021). Anomaly detection in multivariate time series using ensemble method.
[11] Cherukuri, A. K., Ikram, S. T., Li, G., & Liu, X. (2024). Artificial Intelligence-Based Approaches for Anomaly Detection. In Encrypted Network Traffic Analysis (pp. 73-99). Cham: Springer International Publishing.
[12] Khan, W., Usama, M., Khan, M. S., Saidani, O., Al Hamadi, H., Alnazzawi, N., ... & Ahmad, J. (2025). Enhancing security in 6G- enabled wireless sensor networks for smart cities: a multi-deep learning intrusion detection approach. Frontiers in Sustainable Cities, 7, 1580006.
[13] Umair, M., Tan, W. H., & Foo, Y. L. (2024, September). Optimized 1D Convolutional Neural Network for Efficient Intrusion Detection in IoT Networks. In 2024 IEEE 8th International Conference on Signal and Image Processing Applications (ICSIPA) (pp. 1-6). IEEE.
[14] Geetha, K., Srivani, A., Gunasekaran, S., Ananthi, S., & Sangeetha, S. (2023, September). Geospatial data exploration using machine learning. In 2023 4th International Conference on Smart Electronics and Communication (ICOSEC) (pp. 1485-1489). IEEE.
[15] Kalyanaraman, K., & Ponnusamy, S. (2024). AI-Enhanced Optimization Algorithm for Body Area Networks in Intelligent Wearable Patches for Elderly Women's Safety. In Wearable Devices, Surveillance Systems, and AI for Women's Wellbeing (pp. 52-80). IGI Global Scientific Publishing.
[16] Ghorbani, M., Ghassemi, A., Alikhani, M., Khaloozadeh, H., & Nikoofard, A. (2025). Using Kolmogorov–Arnold network for cyber- physical system security: A fast and efficient approach. International Journal of Critical Infrastructure Protection, 100768.
[17] Yang, Y., & Liu, D. (2022, October). MKDNAD: A network flow anomaly detection method based on multi-teacher knowledge distillation. In 2022 16th IEEE International Conference on Signal Processing (ICSP) (Vol. 1, pp. 314-319). IEEE.
[18] Vekkot, S., Chavali, S. T., Kandavalli, C. T., Podila, R. S. A., Gupta, D., Zakariah, M., & Alotaibi, Y. A. (2024). Continuous speech-based fatigue detection and transition state prediction for air traffic controllers. IEEE Access.
[19] Talukder, M. A., Khalid, M., & Sultana, N. (2025). A hybrid machine learning model for intrusion detection in wireless sensor networks leveraging data balancing and dimensionality reduction. Scientific Reports, 15(1), 4617.
[20] Briner, N., Cullen, D., Halladay, J., Miller, D., Primeau, R., Avila, A., & Doleck, T. (2023). Tabular-to-Image transformations for the classification of anonymous network traffic using deep residual networks. IEEE Access, 11, 113100-113113
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Articles in this journal are licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. This license permits others to copy, distribute, and adapt the work, provided it is for non-commercial purposes, and the original author and source are properly credited.
