Keywords
network security monitoring
embedded systems
bidirectional long-short-term memory network
How to Cite
Abstract
With the popularization of smart devices and networked devices, edge device security issues have become increasingly prominent. Traditional security monitoring systems often rely on centralized data processing mode, which is difficult to meet the current real-time analysis requirements of massive data. In order to solve this problem, this paper designs a network edge device security monitoring system based on the fusion of embedded system and bidirectional long-short-term memory network. By deploying the Bi-LSTM model through the embedded processor, the system can detect the abnormal behavior of edge devices in real time, thereby improving the response speed and accuracy of security monitoring. This paper conducts experimental analysis on the actual network traffic data set, collects security data from different types of edge devices, covering device types including smart routers, IoT sensors, etc., and processes more than 100GB of network traffic data in total. The experimental results show that the detection accuracy of the Bi-LSTM model in network attack behavior reaches 96.8%, which is about 4.2% and 5.5% higher than the traditional random forest and support vector machine models respectively. In addition, the real-time analysis of the system shows that the average processing latency of the embedded system is less than 200 ms, which meets the low latency requirement in edge computing environment.
References
Abdi, A., and Salimi-badr, A. DyUnS: Dynamic and uncertainty-aware task scheduling for multiprocessor embedded systems. Sustainable Computing: Informatics and Systems, vol. 43, pp. 101009, 2024.
Dong, Z., Ge, X., Huang, Y., Dong, J., and Xu, J. EG-STC: An Efficient Secure Two-Party Computation Scheme Based on Embedded GPU for Artificial Intelligence Systems. Computers, Materials and Continua, vol. 79 (3), pp. 4021–4044, 2024.
Fareed, A., Hassan, S., Belhaouari, S. B., and Halim, Z. Elevating recommender systems: Cutting-edge transfer learning and embedding solutions. Applied Soft Computing, vol. 166, pp. 112140, 2024.
Gutiérrez-Zaballa, J., Basterretxea, K., and Echanobe, J. Evaluating single event upsets in deep neural networks for semantic segmentation: An embedded system perspective. Journal of Systems Architecture, vol. 154, pp. 103242, 2024.
Hu, K., Huang, W., Wang, L., Mo, C., Wang, R., Chen, Y., Ren, J., and Jiang, B. Unishyper: A Rust-based unikernel enhancing reliability and efficiency of embedded systems. Journal of Systems Architecture, vol. 153, pp. 103199, 2024.
Jin, C., Duan, Y., Zhou, L., and Li, F. Cross-domain recommender system with embedding-and mapping-based knowledge correlation. Knowledge-Based Systems, vol. 304, pp. 112514, 2024.
Li, M., Ma, W., and Chu, Z. KGIE: Knowledge graph convolutionary network for recommender system with interactive embedding. Knowledge-Based Systems, vol. 295, pp. 111813, 2024.
Maruf, M. A., Azim, A., Auluck, N., and Sahi, M. Optimizing DNN training with pipeline model parallelism for enhanced performance in embedded systems. Journal of Parallel and Distributed Computing, vol. 190, pp. 104890, 2024.
Mei, L., Yang, Y., Zhang, X., and Jiang, Y. Embedded exponential Runge-Kutta-Nyström methods for highly oscillatory Hamiltonian systems. Journal of Computational Physics, vol. 514, pp. 113221, 2024.
Niu, L., and Musselwhite, J. Reliability-aware scheduling for (m, k)-firm real-time embedded systems under hard energy budget constraint. Journal of Systems Architecture, vol. 154, pp. 103185, 2024.
Soudré, M. M., Ayala, H. V. H., Melo, A. C., and Llanos, C. H. A novel GPU-based approach for embedded NARMAX/FROLS system identification. Mechanical Systems and Signal Processing, vol. 211, pp. 111261, 2024.
Su, H., Niu, J., Liu, X., and Atiquzzaman, M. SafeCoder: A machine-learning-based encoding system to embed safety identification information into QR codes. Journal of Network and Computer Applications, vol. 227, pp. 103874, 2024.
Zhang, T., Peng, F., Tang, X., Yan, R., Deng, R., and Zhao, S. A sparse knowledge embedded configuration optimization method for robotic machining system toward improving machining quality. Robotics and Computer-Integrated Manufacturing, vol. 90, pp. 102818, 2024.
Atila, Ü., and Sabaz, F. Turkish lip-reading using Bi-LSTM and deep learning models. Engineering Science and Technology, an International Journal, vol. 35, pp. 101206, 2022.
Bibi, N., Maqbool, A., and Rana, T. Enhancing source code retrieval with joint Bi-LSTM-GNN architecture: A comparative study with ChatGPT-LLM. Journal of King Saud University-Computer and Information Sciences, vol. 36 (2), pp. 101865, 2024.
Bukhari, S. M. S., Zafar, M. H., Houran, M. A., Moosavi, S. K. R., Mansoor, M., Muaaz, M., and Sanfilippo, F. Secure and privacy-preserving intrusion detection in wireless sensor networks: Federated learning with SCNN-Bi-LSTM for enhanced reliability. Ad Hoc Networks, vol. 155, pp. 103407, 2024.
Dai, Y., Zhou, Q., Leng, M., Yang, X., and Wang, Y. Improving the Bi-LSTM model with XGBoost and attention mechanism: A combined approach for short-term power load prediction. Applied Soft Computing, vol. 130, pp. 109632, 2022.
Fan, W., Yao, J., Cui, S., Wang, Y., Xu, S., Tan, Y., Yang, F., and Wu, W. Bi-LSTM/GRU-based anomaly diagnosis for virtual network function instance. Computer Networks, vol. 249, pp. 110515, 2024.
Harby, F., Alohali, M., Thaljaoui, A., and Talaat, A. S. Exploring Sequential Feature Selection in Deep Bi-LSTM Models for Speech Emotion Recognition. Computers, Materials and Continua, vol. 78 (2), pp. 2689–2719, 2024.
Miah, M. S. U., Islam, M. I., Islam, S., Ahmed, A., Rahman, M. M., and Mahmud, M. Sustainability-Driven Hourly Energy Demand Forecasting in Bangladesh Using Bi-LSTMs. Procedia Computer Science, vol. 236, pp. 41–50, 2024.
Phukan, R., Goutom, P. J., and Baruah, N. Assamese Fake News Detection: A Comprehensive Exploration of LSTM and Bi-LSTM Techniques. Procedia Computer Science, vol. 235, pp. 2167–2177, 2024.
Riaz, S., Saghir, A., Khan, M. J., Khan, H., Khan, H. S., and Khan, M. J. TransLSTM: A hybrid LSTM-Transformer model for fine-grained suggestion mining. Natural Language Processing Journal, vol. 8, pp. 100089, 2024.
Sambandam, P., Yuvaraj, D., Padmakumari, P., and Swaminathan, S. Deep attention based optimized Bi-LSTM for improving geospatial data ontology. Data & Knowledge Engineering, vol. 144, pp. 102123, 2024.
Wubet, Y. A., and Lian, K.-Y. How can we detect news surrounding community safety crisis incidents in the internet? Experiments using attention-based Bi-LSTM models. International Journal of Information Management Data Insights, vol. 4(1), pp. 100227, 2024.
Yu, K., Kong, C., Zhong, L., Fu, J., and Shao, J. Delay prediction with spatial-temporal bi-directional LSTM in railway network. ICT Express, vol. 9(5), pp. 921–926, 2023.
Ahmed, M., Raza, S., Soofi, A. A., Khan, F., Khan, W. U., Xu, F., Chatzinotas, S., Dobre, O. A., and Han, Z. A survey on reconfigurable intelligent surfaces assisted multi-access edge computing networks: State of the art and future challenges. Computer Science Review, vol. 54, pp. 100668, 2024.
Deng, P., and Huang, Y. Edge-featured multi-hop attention graph neural network for intrusion detection system. Computers & Security, vol. 148, pp. 104132, 2025.
Hazra, A., Tummala, V. M. R., Mazumdar, N., Sah, D. K., and Adhikari, M. Deep reinformation learning in edge networks: Challenges and future directions. Physical Communication, vol. 66, pp. 102460, 2024.
Liu, A., Li, S., Chang, Y., and Hou, Y. EdgeStereoSR: A multi-task network with transformers for stereo image super-resolution considering edge prior. Signal Processing, vol. 227, pp. 109719, 2025.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Journal of Cyber Security and Mobility