An Intelligent Grey Wolf Optimized Hybrid CNNLSTM Assisted Multi Layer Cloud Security Optimization And Threat Detection Framework | Journal of Engineering Strategy and Innovation | JESI
An Intelligent Grey Wolf Optimized Hybrid CNNLSTM Assisted Multi Layer Cloud Security Optimization And Threat Detection Framework
Author(s) RegistryKajal Sheth, Dheeraj Kumar Bansal, K. Madhuvandhana
Volume & IssueVol 1, Iss 01
Acceptance Date23 Jun 2026
Publication Date14 Jul 2026
Digital DOI Handle*
Abstract
Cloud computing infrastructures are highly vulnerable to advanced attacks due to their multi-tenant structure, distributed nature, and dynamic resource allocation. It has been a serious issue to maintain computing efficiency and robust security in multiple cloud levels. The proposed approach adopts LSTM network for recognizing temporal patterns of attacks in cloud computing traffic data along with CNN for efficient spatial feature extraction. Moreover, GWO algorithm is employed in order to minimize computing cost, tune the parameter values of the model, and increase detection accuracy. Multiple security layers are applied in order to observe and protect cloud infrastructure, platform, and application layers from diverse types of cyber-attacks. Experimental analysis proves that the proposed framework provides better performance than conventional machine learning (ML) and deep learning (DL) models in terms of threat detection, higher precision and recall values, lower false positive rate, and security optimization.
Deore, Bhushan, and Surendra Bhosale. "Hybrid optimization enabled robust CNN-LSTM technique for network intrusion detection." Ieee Access 10 (2022). 65611-65622.
Manokaran, J., and G. Vairavel. "Dl-ads. Improved grey wolf optimization enabled ae-lstm technique for efficient network anomaly detection in internet of thing edge computing." IEEE
Access 12 (2024). 75983-76002.
Pyari, Dayal, Abothu Geetha, B. Kumar Babu, M. Misba, Veera Ankalu Vuyyuru, and B. Kiran Bala. "Enhancing Cloud Computing Security through Hybrid CNN-LSTM and Advanced Data Mining Techniques." In 2024 Third International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), pp. 1-6. IEEE, 2024.
Zavvar, Mohammad, Keyvan Karamnejadi Azar, Mahmoudreza Entezami, Masoumeh Asgharighajari, Armin Zakarian, Alireza Golkarieh, Ali Akbar Kiaei, Arash Heidari, and Nima Jafari Navimipour. "A hybrid
intrusion detection method based on multi-convolutional neural networks fusion and grey wolf optimizer." Journal of
Cloud Computing 15, no. 1 (2026). 77.
Sinha, Priyanshu, Dinesh Sahu, Shiv Prakash, Tiansheng Yang, Rajkumar Singh Rathore, and Vivek Kumar Pandey. "A high performance hybrid LSTM CNN secure architecture for IoT environments using deep learning." Scientific Reports 15 (2025). 9684.
Poddar, Sanjay, Swagata Aswani, Ram Chandra Sachan, Venkata Nedunoori, and Udit Patel. "Enhancing Cloud Network Security With Hybrid Cnn-Lstm Models for Intrusion Detection." In 2024 IEEE 11th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), pp. 1-5. IEEE, 2024.
Akilandeswari, S., T. R. Soumya, S. Sumathi, Mishmala Sushith, V. Brinda, and S. Rajan. "A hybrid cnn-lstm-pso framework for enhanced cybersecurity threat detection and classification." In 2025 International Conference on Multi- Agent Systems for Collaborative Intelligence (ICMSCI), pp. 1956-1965. IEEE, 2025.
Abid, Tarek, Ahmed Ahmim, Faiz Maazouzi, Djalel Chefrour, Insaf Ullah, Marwa Ahmim, and Reham Almukhlifi. "A novel IoT threat detection using GWO attribute selection and CNN- enhanced LightGBM." Journal of Cloud Computing 14, no. 1 (2025). 72.
Munawar, Adeel, Muhammad Nadeem Ali, Awais Qasim, and Kim Byung-Seo. "GWO-LightGBM. A Hybrid Grey Wolf Optimized Light Gradient Boosting Model for Cyber-Physical System Security." Computer Modeling in Engineering &
Maria Priska A, Dr.K.Madhan Kumar, Mrs.X.M.Binisha, &
Ms.K.Sneha. (2025). Novel And Hybrid Frameworks for Attack Detection And Secure Transmission in Manet. International Journal of Advanced Engineering and Management System, 1(3), 204 -213. https://doi.org/10.65379/tpsn2013/ijaemsv01i03p3
Attou, Hanaa, Azidine Guezzaz, Said Benkirane, Mourade Azrour, and Yousef Farhaoui. "Cloud-based intrusion detection approach using machine learning techniques." Big
Data Mining and Analytics 6, no. 3 (2023). 311-320.
Elsayed, Eslam Bokhory, Abdalla Sayed Yassin, and Hanan Fahmy. "A Novel Hybrid GWO-RFO Metaheuristic Algorithm for Optimizing 1D-CNN Hyperparameters in IoT Intrusion
Detection Systems." Information 16, no. 12 (2025). 1103.
Halbouni, Asmaa, Teddy Surya Gunawan, Mohamed Hadi Habaebi, Murad Halbouni, Mira Kartiwi, and Robiah Ahmad. "CNN-LSTM. hybrid deep neural network for network intrusion detection system." IEEE access 10 (2022). 99837-
R. Divya et al., "ResidualFormer: A Hybrid CNN-Based Encoder with Segformer-Inspired Decoder for Efficient Semantic Segmentation," Journal of Progressive Engineering Studies (JPES), vol. 1, no. 1, pp. 46-55, 2026.
Hepsiba. D et al., "Dynamic Task Offloading Optimization in Mobile Edge Computing Using Graph-Attention Multi-Agent Reinforcement Learning," Journal of Progressive Engineering Studies (JPES), vol. 1, no. 1, pp. 29-45, 2026.
Dr.P.Aravindan, & Saravanaraj.M (2026). Simulation-Based CNN-LSTM Fault Detection Framework for Grid-Connected Solar PV Systems. International Journal of Advanced Engineering and Management System, 2(2), 355-365. https://doi.org/10.65379/IJAEMS/V2-I2-08Jun2026-P78
R, K., Kumar, T., Balamurugan, K., Menaka, S., Suganya, S., & Singaravel, G. (2026). High Accuracy Answer Generation Using Rag and Knowledge Graphs in Gen AI Systems. International Journal of Advanced Engineering and Management System, 2(2), 308 -315. https://doi.org/10.65379/IJAEMS/V2-I2-18May2026-P73
An Intelligent Grey Wolf Optimized Hybrid CNNLSTM Assisted Multi Layer Cloud Security Optimization And Threat Detection Framework
[1] K. Sheth, D. K. Bansal, K. Madhuvandhana, "An Intelligent Grey Wolf Optimized Hybrid CNNLSTM Assisted Multi Layer Cloud Security Optimization And Threat Detection Framework," *Journal of Engineering Strategy and Innovation (JESI)*, vol. 1, no. 1, pp. 25-31, 2026.
