CyberShieldDL: A Hybrid Deep Learning Architecture for Robust Intrusion Detection and Cyber Threat Classification

Authors

S. Venkatramulu
Kakatiya Institute of Technology and Science, Warangal, Telangana, India
John Babu Guttikonda
Anurag Engineering College, Kodad, Telangana
Desidi Narsimha Reddy
Data Consultant (Data Governance ,Data Analytics,EPM: enterprise performance management,AI&ML), Soniks consulting LLC,USA.
Y. Madhavi   Reddy
CVR COLLEGE OF ENGINEERING, IBRAHIMPATNAM, Telangana , India
M. Sirisha
PhD scholar, Department Data science,kL University,Vijayawada, AndhraPradesh India
DOI: https://doi.org/10.52549/ijeei.v13i3.6912
Download PDF
Published: 17-09-2025 • Issue: Vol. 13 No. 3: September 2025 • Section: Regular paper

Abstract

In modern network environments, securing systems from newly emerging attacks is essential, and a constructive approach is the use of an IDS (Intrusion Detection System). When faced with attacks that are not in the list of predefined patterns, traditional IDS methods such as signature-based detection or standalone machine learning models may not function properly to detect such attacks because they are not adaptable and not designed to deal with this type of attack. The current IDS systems that employ deep-learning architectures have enhanced detection capabilities; however, most prior art systems are limited by partial feature learning, which only learns features of either spatial or temporal traffic structures. Meanwhile, the lack of contextaware mechanisms, such as attention, limits their ability to attend more to the most informative network components, leading to suboptimal detection performance and generalization. To counter this issue, in this work, we introduce CyberShieldDL, which is the first deep learning-based IDS framework with a novel hybrid architecture: IntruNet-Hybrid, combining Convolutional Neural Networks (CNN) for spatial pattern extraction, Bidirectional Long Short-Term Memory (Bi-LSTM) networks for sequential feature extraction, and an attention mechanism to learn the salient features for intrusion detection dynamically. To create the framework, an optimized preprocessing and feature selection pipeline is presented to effectively and costeffectively prepare the model input. Extensive experiments on the CICIDS2017 dataset demonstrate that CyberShieldDL consistently outperforms the state-of-the-art, achieving an overall accuracy of 98.35% and high precision, recall, and F1-score in various attack scenarios. Cross-dataset validations on NSL-KDD and UNSW-NB15 also verify the system's generalization. The design provides a scalable and flexible solution for realworld network security, offering the flexibility and adaptability necessary to enhance classification accuracy and robustness against evolving attack patterns. Its modular construction enables us to extend it for real-time deployment and future adversarial robustness easily.
Keywords: Intrusion Detection System; Deep Learning; CNN-BiLSTM; Attention Mechanism; Network Security

References

Asmaa Halbouni, Teddy Surya Gunawan, Mohamed Hadi Habaebi, Murad Halbouni, Mira Kartiwi, and Robiah Ahmad. (2022). CNN-LSTM: a hybrid deep neural network for a network intrusion detection system. IEEE. 10, pp.99837 - 99849. DOI:10.1109/ACCESS.2022.3206425

Vanlalruata Hnamte, and Jamal Hussain. (2023). DCNNBiLSTM: An efficient hybrid deep learning-based intrusion detection system. Elsevier. 10, pp.1-13. https://doi.org/10.1016/j.teler.2023.100053

Lansky, J., Ali, S., Mohammadi, M., Majeed, M. K., Karim, S. H. T., Rashidi, S., … Rahmani, A. M. (2021). Deep Learning-Based Intrusion Detection Systems: A Systematic Review. IEEE Access, 9, 101574–101599. doi:10.1109/access.2021.3097247

Afrah Gueriani, Hamza Kheddar, and Ahmed Cherif Mazari. (2024). Enhancing iot security with cnn and lstm-based intrusion detection systems. IEEE., pp.1-7. DOI:10.1109/PAIS62114.2024.10541178

Vanlalruata Hnamte, Hong Nhung-Nguyen, Jamal Hussain, and Yong Hwa-Kim. (2023). A novel two-stage deep learning model for network intrusion detection: LSTM-AE. IEEE. 11, pp.37131 - 37148. DOI:10.1109/ACCESS.2023.3266979

Hakan Can Altunay, and Zafer Albayrak. (2023). A hybrid CNN+ LSTM-based intrusion detection system for industrial IoT networks. Elsevier. 38, pp.1-13. https://doi.org/10.1016/j.jestch.2022.101322

Babatunde Olanrewaju-George, and Bernardi Pranggono. (2025). Federated learning-based intrusion detection system for the internet of things using unsupervised and supervised deep learning. Elsevier. 3, pp.1-10. https://doi.org/10.1016/j.csa.2024.100068

Abdelwahed Berguiga, Ahlem Harchay, and Ayman Massaoudi. (2025). HIDS-IoMT: A deep Learning-Based intelligent intrusion detection system for the internet of medical things. IEEE. 13, pp.32863 - 32882. DOI:10.1109/ACCESS.2025.3543127

Tamara Al-Shurbaji, Mohammed Anbar, Selvakumar Manickam, Iznan H Hasbullah, Nadia Alfriehat, Basim Ahmad Alabsi, Ahmad Reda Alzighaibi, and Hasan Hashim. (2025). Deep Learning-Based Intrusion Detection System For Detecting IoT Botnet Attacks: A Review. IEEE. 13, pp.11792 - 11822. DOI:10.1109/ACCESS.2025.3526711

Abdelwahed Berguiga, Ahlem Harchay, and Ayman Massaoudi. (2025). HIDS-RPL: A Hybrid Deep Learning-Based Intrusion Detection System for RPL in Internet of Medical Thing Networks. IEEE. 13, pp.38404 - 38429. DOI:10.1109/ACCESS.2025.3545918

I. A. Fares et al., "Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT Environment," in IEEE Open Journal of the Communications Society, vol. 6, pp. 4342-4365, 2025, doi: 10.1109/OJCOMS.2025.3569301.

Rania Aboalela, Khalid H. Allehaibi, Louai A. Maghrabi, Naif Alsaadi, Ehab Bahaudien Ashary, Almuhannad S. Alorfi, Wajdi Alghamdi, and Mahmoud Ragab. (2025). Harnessing feature pruning with optimal deep learning-based distributed denial of service cyberattack detection on IoT environment. Elsevier. 120, pp.584-597. https://doi.org/10.1016/j.aej.2025.02.070

A. Al Mazroa, F. R. Albogamy, M. Khairi Ishak and S. M. Mostafa, "Boosting Cyberattack Detection Using Binary Metaheuristics With Deep Learning on Cyber-Physical System Environment," in IEEE Access, vol. 13, pp. 11280- 11294, 2025, doi: 10.1109/ACCESS.2025.3526258.

M. A. S. P. Dayarathne, M. S. M. Jayathilaka, R. M. V. A. Bandara, V. Logeeshan, S. Kumarawadu and C. Wanigasekara, "Mitigating Cyber Risks in Smart Cyber-Physical Power Systems Through Deep Learning and Hybrid Security Models," in IEEE Access, vol. 13, pp. 37474-37492, 2025, doi: 10.1109/ACCESS.2025.3545637.

S. Hariharan, Y. Annie Jerusha, G. Suganeshwari, S. P. Syed Ibrahim, U. Tupakula and V. Varadharajan, "A Hybrid Deep Learning Model for Network Intrusion Detection System Using Seq2Seq and ConvLSTM-Subnets," in IEEE Access, vol. 13, pp. 30705-30721, 2025, doi: 10.1109/ACCESS.2025.3541399.

Fatimah Alhayan, Alanoud Subahi, Muhammad Kashif Saeed, Nouf Atiahallah Alghanmi, Randa Allafi, Monir Abdulla, Hanadi Alkhudhayr. (2025). Hybrid deep learning models with spotted hyena optimization for cloud computing enabled intrusion detection system. Elsevier. 18(2), pp.1-12. https://doi.org/10.1016/j.jrras.2025.101523

R. Manivannan, and S. Senthilkumar. (2025). Intrusion detection system for network security using novel adaptive recurrent neural network-based fox optimizer concept. Springer. 18(37), pp.1-24. https://doi.org/10.1007/s44196- 025-00767-x

Mohammad Zubair Khan, Aijaz Ahmad Reshi, Shabana Shafi, and Ibrahim Aljubayri. (2025). An adaptive hybrid framework for IIoT intrusion detection using neural networks and feature optimization using genetic algorithms. Springer. 6(382), pp.1-20. https://doi.org/10.1007/s43621-025-01141-9

Yanxia Sun, and Zenghui Wang. (2025). Intrusion detection in IoT and wireless networks using image-based neural network classification. Elsevier. 177, pp.1-17. https://doi.org/10.1016/j.asoc.2025.113236

Salahaldeen Duraibi, and Abdullah Mujawib Alashjaee. (2024). Enhancing Cyberattack Detection Using Dimensionality Reduction With Hybrid Deep Learning on Internet of Things Environment. IEEE. 12, pp.84752 - 84762. DOI:10.1109/ACCESS.2024.3411612

Huma, Z. E., Latif, S., Ahmad, J., Idrees, Z., Ibrar, A., Zou, Z., … Baothman, F. (2021). A Hybrid Deep Random Neural Network for Cyberattack Detection in the Industrial Internet of Things. IEEE Access, 9, 55595–55605. doi:10.1109/access.2021.3071766

M. Ozkan-Okay, Ö. Aslan, R. Eryigit and R. Samet, "SABADT: Hybrid Intrusion Detection Approach for Cyber Attacks Identification in WLAN," in IEEE Access, vol. 9, pp. 157639-157653, 2021, doi: 10.1109/ACCESS.2021.3129600.

Ho, S., Jufout, S. A., Dajani, K., & Mozumdar, M. (2021). A Novel Intrusion Detection Model for Detecting Known and Innovative Cyberattacks Using Convolutional Neural Network. IEEE Open Journal of the Computer Society, 2, 14–25. doi:10.1109/ojcs.2021.3050917

A. A. Elsaeidy, A. Jamalipour and K. S. Munasinghe, "A Hybrid Deep Learning Approach for Replay and DDoS Attack Detection in a Smart City," in IEEE Access, vol. 9, pp. 154864-154875, 2021, doi: 10.1109/ACCESS.2021.3128701.

ElSayed, M. S., Le-Khac, N.-A., Albahar, M. A., & Jurcut, A. (2021). A novel hybrid model for intrusion detection systems in SDNs based on CNN and a new regularization technique. Journal of Network and Computer Applications, 191, 103160. doi:10.1016/j.jnca.2021.103160

Otoum, Y., & Nayak, A. (2021). AS-IDS: Anomaly and Signature Based IDS for the Internet of Things. Journal of Network and Systems Management, 29(3). doi:10.1007/s10922-021-09589-6

Rajesh Kanna, P., & Santhi, P. (2021). Unified Deep Learning approach for Efficient Intrusion Detection System using Integrated Spatial–Temporal Features. Knowledge-Based Systems, 226, 107132. doi:10.1016/j.knosys.2021.107132

Jin, S., Chung, J.-G., & Xu, Y. (2021). Signature-Based Intrusion Detection System (IDS) for In-Vehicle CAN Bus Network. 2021 IEEE International Symposium on Circuits and Systems (ISCAS). doi:10.1109/iscas51556.2021.9401087

Applebaum, S., Gaber, T., & Ahmed, A. (2021). Signature-based and Machine-Learning-based Web Application Firewalls: A Short Survey. Procedia Computer Science, 189, 359–367. doi:10.1016/j.procs.2021.05.105

M. H. Shahriar, Y. Xiao, P. Moriano, W. Lou and Y. T. Hou, "CANShield: Deep-Learning-Based Intrusion Detection Framework for Controller Area Networks at the Signal Level," in IEEE Internet of Things Journal, vol. 10, no. 24, pp. 22111-22127, 15 Dec.15, 2023, doi: 10.1109/JIOT.2023.3303271.

K. Yu, K. Nguyen and Y. Park, "Flexible and Robust Real-Time Intrusion Detection Systems to Network Dynamics," in IEEE Access, vol. 10, pp. 98959-98969, 2022, doi: 10.1109/ACCESS.2022.3199375.

R. Ben Said, Z. Sabir and I. Askerzade, "CNN-BiLSTM: A Hybrid Deep Learning Approach for Network Intrusion Detection System in Software-Defined Networking With Hybrid Feature Selection," in IEEE Access, vol. 11, pp. 138732-138747, 2023, doi: 10.1109/ACCESS.2023.3340142.

Sydney Mambwe Kasongo. (2023). A deep learning technique for intrusion detection system using a Recurrent Neural Networks based framework. Elsevier. 199, pp.113-125. https://doi.org/10.1016/j.comcom.2022.12.010

J. Du, K. Yang, Y. Hu and L. Jiang, "NIDS-CNNLSTM: Network Intrusion Detection Classification Model Based on Deep Learning," in IEEE Access, vol. 11, pp. 24808-24821, 2023, doi: 10.1109/ACCESS.2023.3254915.

Y. A. Jerusha, S. P. S. Ibrahim and V. Varadharajan, "A Novel Semantic Driven Meta-Learning Model for Rare Attack Detection," in IEEE Access, vol. 13, pp. 73219-73235, 2025, doi: 10.1109/ACCESS.2025.3564031.

Kocher, G., & Kumar, G. (2021). Machine learning and deep learning methods for intrusion detection systems: recent developments and challenges. Soft Computing, 25(15), 9731–9763. doi:10.1007/s00500-021-05893-0

Fazil, M., Sah, A. K., & Abulaish, M. (2021). DeepSBD: A Deep Neural Network Model With Attention Mechanism for SocialBot Detection. IEEE Transactions on Information Forensics and Security, 16, 4211–4223. doi:10.1109/tifs.2021.3102498

Sun, H., Chen, M., Weng, J., Liu, Z., & Geng, G. (2021). Anomaly Detection for In-Vehicle Network using CNNLSTM with Attention Mechanism. IEEE Transactions on Vehicular Technology, 1–1. doi:10.1109/tvt.2021.3106940

K. Yin, Y. Yang, C. Yao and J. Yang, "Long-Term Prediction of Network Security Situation Through the Use of the Transformer-Based Model," in IEEE Access, vol. 10, pp. 56145-56157, 2022, doi: 10.1109/ACCESS.2022.3175516.

T. V. Dao, H. Sato and M. Kubo, "An Attention Mechanism for Combination of CNN and VAE for Image-Based Malware Classification," in IEEE Access, vol. 10, pp. 85127-85136, 2022, doi: 10.1109/ACCESS.2022.3198072.

Canadian Institute for Cybersecurity, 2017. CIC-IDS2017 Dataset. [online] Available at: https://www.unb.ca/cic/datasets/ids-2017.html.

Tavallaee, M., Bagheri, E., Lu, W. and Ghorbani, A., 2009. A Detailed Analysis of the KDD CUP 99 Dataset: Improving the KDD99 Dataset. In: Proceedings of the 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications. IEEE, pp.1-6. [online] Available at: https://www.unb.ca/cic/datasets/nsl.html.

Moustafa, N. and Slay, J., 2015. UNSW-NB15: A Comprehensive Data Set for Network Intrusion Detection Systems (UNSW-NB15 Network Data Set). In: Military Communications and Information Systems Conference (MilCIS). IEEE, pp.1-6. [online] Available at: https://research.unsw.edu.au/projects/unsw-nb15-dataset.

Udurume, M., Shakhov, V. & Koo, I. (2024) ‘Comparative analysis of deep convolutional neural network— bidirectional long short-term memory and machine learning methods in intrusion detection systems’, Applied Sciences, 14(16), p.6967.

Xu, H., Sun, L., Fan, G., Li, W. & Kuang, G. (2023) ‘A hierarchical intrusion detection model combining multiple deep learning models with attention mechanism’, IEEE Access, 11, pp.66212–66226.

Hassan, M.M., Gumaei, A., Alsanad, A., Alrubaian, M. & Fortino, G. (2020) ‘A hybrid deep learning model for efficient intrusion detection in big data environment’, Information Sciences, 513, pp.386–396.

Qazi, E.U.H., Faheem, M.H. & Zia, T. (2023) ‘HDLNIDS: hybrid deep-learning-based network intrusion detection system’, Applied Sciences, 13(8), p.4921.

Aldallal, A. (2022) ‘Toward efficient intrusion detection system using hybrid deep learning approach’, Symmetry, 14(9), p.1916.

Mayuranathan, M., Saravanan, S.K., Muthusenthil, B. & Samydurai, A. (2022) ‘An efficient optimal security system for intrusion detection in cloud computing environment using hybrid deep learning technique’, Advances in Engineering Software, 173, p.103236.

Sajid, M., Malik, K.R., Almogren, A., Malik, T.S., Khan, A.H., Tanveer, J. & Rehman, A.U. (2024) ‘Enhancing intrusion detection: a hybrid machine and deep learning approach’, Journal of Cloud Computing, 13(1), p.123.

Sharma, A., Rani, S. & Driss, M. (2024) ‘Hybrid evolutionary machine learning model for advanced intrusion detection architecture for cyber threat identification’, PLOS ONE, 19(9), p.e0308206.

Author Biographies

S. Venkatramulu
Associate Professor, Department of CSE(Networks)
John Babu Guttikonda
Associate Professor, Department of Computer Science & Engineering(AI & ML)
Y. Madhavi   Reddy
Assistant professor, Department  H&S (Mathematics)

How to Cite

[1]
S. Venkatramulu, J. B. Guttikonda, D. N. Reddy, Y.M. Reddy, and M. Sirisha, “CyberShieldDL: A Hybrid Deep Learning Architecture for Robust Intrusion Detection and Cyber Threat Classification”, IJEEI, vol. 13, no. 3, pp. 645–667, Sep. 2025, doi: 10.52549/ijeei.v13i3.6912.