submit paper now

🗂️ IJET Current Issue 🎓 , , , , , ,

Comprehensive Survey of Deep Learning-Based Intrusion Detection for IoT Wireless Sensor Networks – Volume 11 Issue 5 | Satish Dekka | IJET Journal 2025

IJET – International Journal of Engineering and Techniques
International Journal of Engineering and Techniques (IJET)
Open Access • Peer Reviewed • High Citation & Impact Factor • ISSN: 2395-1303
IJET-V11I5P16  |  Volume 11 Issue 5  |  September – October 2025

Comprehensive Survey of Deep Learning-Based Intrusion Detection for Securing Routing in IoT Wireless Sensor Networks

Authors: SATISH DEKKA , Dr. PRASADU PEDDI , Dr. MANENDRA SAI DASARI
SATISH DEKKA — Research Scholar, Shri JJT University, Rajasthan.
Dr. PRASADU PEDDI — Guide, Shri JJT University, Rajasthan.
Dr. MANENDRA SAI DASARI — Co-Guide, Shri JJT University, Rajasthan.

Abstract

The proliferation of Internet of Things (IoT) Wireless Sensor Networks (WSNs) incritical sectors demands robust security solutions to counter complex routing attacks such as sinkhole, blackhole, and selective forwarding. Conventional detection methods often fall short inresource-constrained, dynamic IoT WSN environments. Deep Learning (DL) techniquesincluding Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), andAutoencoders have shown remarkable ability to autonomously detect and classifyroutingsecurity threats with high accuracy. This comprehensive survey systematically reviews recent DL-based Intrusion DetectionSystems (IDS) designed to secure routing in IoT WSNs. It examines key DL architectures, evaluates their performance using benchmark datasets and metrics, and discusses challengesincluding real-time deployment, energy efficiency, and model interpretability. Finally, thepaper outlines future research directions toward developing lightweight, adaptive, anddistributed DL-IDS specifically tailored for IoT WSNs

Keywords

Deep Learning, Intrusion Detection System, IoT Wireless Sensor Networks, Routing Security, Routing Attacks, CNN, RNN, Autoencoders, Lightweight Models

Conclusion

Routing attacks represent a major threat to IoT-enabled Wireless Sensor Networks (WSNs), impacting data integrity, availability, and energy efficiency. Traditional security mechanisms International Journal of Engineering and Techniques-Volume 11 Issue5, September – October – 2025 ISSN: 2395-1303 https://ijetjournal.org/ Page180and classical IDS lack the adaptability needed for dynamic and zero-day attacks inIoTenvironments. Deep Learning (DL)-based IDS show great promise by learning complextraffic patterns, detecting anomalies, and providing adaptive protection. This survey reviewed key routing attacks and analyzed DL architectures—such as CNN, LSTM, Autoencoders, DBNs, and hybrid models—applied to IoT-WSNsecurity. Hybridmodels, federated learning, and edge-based deployments provide enhanced accuracyandresilience but face challenges in computational cost and real-time implementation. Future research should focus on lightweight DL models for constrained nodes, federatedandedge-based learning for privacy and efficiency, richer multi-protocol datasets, explainableAIfor better trust, and hybrid multi-layered security frameworks. Overall, DL-based IDS offer a compelling solution for securing IoT routing protocols, but practical adoption requires balancing resource demands, interpretability, and responsiveness. This survey lays the groundwork for developing effective, tailored IDS solutions for IoT-enabled WSNs.
Key Observations and Future Directions
  1. Lightweight DL models for energy-limited IoT nodes.
  2. Federated and edge-based DL-IDS to ensure privacy and low latency.
  3. Realistic multi-protocol IoT-WSN datasets for better benchmarking.
  4. Explainable AI for transparency and trust.
  5. Hybrid and multi-layered security frameworks for robust protection

References

  1. Y. Zhang, J. Li, and H. Wang, “A CNN-based intrusion detection systemfor routingattacks in IoT-enabled WSNs,” IEEE Access, vol. 9, pp. 12345–12358, 2021.
  2. S. Li, X. Chen, and Y. Zhang, “LSTM-based detection of selective forwardingandwormhole attacks in RPL IoT networks,” Journal of Network and ComputerApplications, vol. 157, pp. 102–115, 2020.
  3. A. Ahmed, M. Yousaf, and F. Khan, “Autoencoder-based anomaly detectionfor IoT-enabled wireless sensor networks,” Computer Networks, vol. 165, pp. 106–118, 2019.
  4. P. Kumar, R. Singh, and D. Sharma, “Hybrid CNN-LSTMintrusion detectionforAODV and DSDV routing in IoT-WSNs,” Future Generation Computer Systems, vol. 125, pp. 55–70, 2022.
  5. R. Singh, S. Kumar, and A. Patel, “Federated CNN-based IDS for privacy-preservingsecurity in RPL IoT networks,” IEEE Internet of Things Journal, vol. 8, no. 12, pp. 9876–9888, 2021.
  6. C. Chen, H. Li, and Y. Zhao, “Deep Belief Network based intrusion detectionforLEACH routing in IoT-WSNs,” Sensors, vol. 20, no. 14, pp. 4023, 2020.
  7. H. Zhang, Z. Zhang, and X. Zhang, “Development of an intelligent intrusion detectionsystem for IoT networks,” Journal of Intelligent & Fuzzy Systems, vol. 39, no. 4, pp. 1–12, 2025.
  8. A. Aldhaheri, A. Al-Dubai, and A. K. Sangaiah, “Deep learning for cyber threat detection in IoT networks,” Computers, Materials & Continua, vol. 71, no. 1, pp. 1–15, 2024.
  9. M. Nakıp and E. Gelenbe, “Online self-supervised deep learning for intrusiondetection systems,” arXiv preprint arXiv:2306.13030, 2023.
  10. H. Barati, “A quantum genetic algorithm-enhanced self-supervised intrusion detectionsystem for wireless sensor networks in the Internet of Things,” arXivpreprint arXiv:2509.03744, 2025.
  11. S. Jamshidia, A. Nikanjama, and F. Khomha, “Application of deep reinforcement learning for intrusion detection in Internet of Things: A systematic review,” arXivpreprint arXiv:2504.14436, 2025.
  12. A. Gueriani, H. Kheddar, and A. Cherif Mazari, “Deep Reinforcement LearningforIntrusion Detection in IoT: A Survey,” arXiv preprint arXiv:2405.20038, 2024.
  13. M. M. Rahman, M. S. Hossain, and M. A. Hossain, “A survey on intrusion detectionsystem in IoT networks,” Computers, Materials & Continua, vol. 72, no. 3, pp. 1–20, 2025.
  14. R. Chinnasamy, S. S. S. R. Depuru, and R. K. Gupta, “Deep learning-driven methodsfor network-based intrusion detection systems,” Journal of King Saud University-Computer and Information Sciences, 2025.
  15. G. G. Gebremariam, “Design of advanced intrusion detection systems basedondeeplearning for wireless sensor networks,” Journal of Network and ComputerApplications, vol. 175, pp. 102–115, 2023.
  16. F. S. Alsubaei, “Smart deep learning model for enhanced IoTintrusiondetection,” Scientific Reports, vol. 15, no. 1, pp. 1–10, 2025.
  17. A. Awajan, “A novel deep learning-based intrusion detection systemfor IoTdevices,” Computers, vol. 12, no. 2, pp. 34, 2023.
  18. M. M. Rahman, M. S. Hossain, and M. A. Hossain, “IoT intrusion detectioninwireless sensor networks,” AIP Conference Proceedings, vol. 3279, pp. 020068, 2025.
Discoverable via Google Scholar • IJET: https://ijetjournal.org/

Citation & DOI Information

Recommended Citation:
Satish Dekka, Dr. Prasadu Peddi, Dr. Manendra Sai Dasari (2025). Comprehensive Survey of Deep Learning-Based Intrusion Detection for Securing Routing in IoT Wireless Sensor Networks. International Journal of Engineering and Techniques (IJET), Volume 11 Issue 5, September – October 2025.

DOI registered via Zenodo · Indexed in Google Scholar for global academic discoverability.
deep-learning-intrusion-detection-iot-wireless-sensor-networks-satish-dekka-ijetDownload
Tag

Related Posts