Wireless Sensor Networks (WSNs) form the backbone of Internet of Things (IoT) ecosystems, enabling pervasive data collection and communication. However, the inherent constraints of sensor nodes limited energy, processing power, and memorycoupled with deployment in open environments, create significant security vulnerabilities and routing challenges. This paper proposes a novel framework integrating deep learning-based attack prediction, optimized clustering, collision-aware routing, and homomorphic encryption for secure and energy-efficient data transmission in WSN-IoT environments. The proposed methodology first identifies malicious nodes using a deep learning classifier, followed by optimized clustering and cluster head selection using an enhanced metaheuristic algorithm. A collision-aware routing protocol selects optimal paths for data transmission, while homomorphic encryption ensures end-to-end data security without decryption overhead. Simulation results demonstrate significant improvements in network lifetime, packet delivery ratio, energy consumption, and end-to-end delay compared to existing approaches.
Introduction
This research focuses on improving security and energy efficiency in Wireless Sensor Networks (WSNs) within the Internet of Things (IoT). IoT enables seamless communication between interconnected devices, while WSNs play a key role in sensing and data collection. However, these networks face major challenges due to limited sensor energy, vulnerability to attacks, packet collisions, and inefficient routing, especially in large-scale deployments.
The study highlights that existing solutions often address either security or energy efficiency but rarely both together. Many centralized and traditional routing approaches fail to scale and introduce issues such as high energy consumption, delays, and reduced network lifetime. Additionally, low-power sensor nodes are highly vulnerable to attacks due to limited computational and storage capabilities.
To overcome these limitations, the proposed framework introduces a machine learning and deep learning-based secure routing system. It includes:
Deep Neural Network (DNN) for early detection of malicious nodes
PSO-based clustering for optimized cluster head selection and energy balancing
Modified A algorithm (SEERP)* for secure and energy-efficient path selection
CSMA/CA enhancement for reducing packet collisions
Paillier homomorphic encryption for secure end-to-end data transmission
The system is implemented using Python and TensorFlow, with simulation parameters such as network size, node energy, and transmission range defined for performance evaluation.
Conclusion
This paper proposed a comprehensive framework for secure and energy-efficient data transmission in WSN-IoT environments integrating deep learning-based attack prediction, optimized clustering, collision-aware routing, and homomorphic encryption. The proposed methodology effectively addresses key challenges including malicious node detection, energy conservation, packet collision reduction, and data security.Simulation results demonstrate significant performance improvements: 26% increase in network lifetime, 89%+ packet delivery ratio even under 30% malicious nodes, 119% improvement in residual energy retention at round 1000, 28% reduction in end-to-end delay, and robust security properties including confidentiality, integrity, authentication, and privacy-preserving computation.Future work will extend this framework to underwater WSN environments, integrate blockchain for enhanced trust management, and explore lightweight homomorphic encryption variants for resource-constrained nodes.
References
[1] Deebak, B.D. and Al-Turjman, F., 2020. A hybrid secure routing and monitoring mechanism in IoT-based wireless sensor networks. Ad Hoc Networks, 97, p.102022. DOI: 10.1016/j.adhoc.2019.102022
[2] Haseeb, K., Almogren, A., Islam, N., Ud Din, I. and Jan, Z., 2019. An energy-efficient and secure routing protocol for intrusion avoidance in IoT-based WSN. Energies, 12(21), p.4174. DOI: 10.3390/en12214174
[3] Ali, T., Irfan, M., Shaf, A., Saeed Alwadie, A., Sajid, A., Awais, M. and Aamir, M., 2020. A secure communication in IoT enabled underwater and wireless sensor network for smart cities. Sensors, 20(15), p.4309. DOI: 10.3390/s20154309
[4] Elhoseny, M. and Shankar, K., 2019. Reliable data transmission model for mobile ad hoc network using signcryption technique. IEEE Transactions on Reliability, 69(3), pp.1077-1086. DOI: 10.1109/TR.2019.2915800
[5] Srivastava, A., Singh, A., Joseph, S.G., Rajkumar, M., Borole, Y.D. and Singh, H.K., 2021. WSN-IoT Clustering for Secure Data Transmission in E-Health Sector using Green Computing Strategy. In 2021 9th International Conference on Cyber and IT Service Management (CITSM) (pp. 1-8). IEEE. DOI: 10.1109/CITSM52892.2021.9588865
[6] Naghibi, M. and Barati, H., 2021. SHSDA: secure hybrid structure data aggregation method in wireless sensor networks. Journal of Ambient Intelligence and Humanized Computing, 12(12), pp.10769-10788. DOI: 10.1007/s12652-020-02864-z
[7] Ostad-Sharif, A., Arshad, H., Nikooghadam, M. and Abbasinezhad-Mood, D., 2019. Three party secure data transmission in IoT networks through design of a lightweight authenticated key agreement scheme. Future Generation Computer Systems, 100, pp.882-892. DOI: 10.1016/j.future.2019.05.062
[8] Verma, S., Zeadally, S., Kaur, S. and Sharma, A.K., 2021. Intelligent and secure clustering in wireless sensor network (WSN)-based intelligent transportation systems. IEEE Transactions on Intelligent Transportation Systems, 23(8), pp.13473-13481. DOI: 10.1109/TITS.2021.3124825
[9] Salau, A.O., Marriwala, N. and Athaee, M., 2021. Data security in wireless sensor networks: Attacks and countermeasures. In Mobile Radio Communications and 5G Networks (pp. 173-186). Springer Singapore. DOI: 10.1007/978-981-15-7130-5_14
[10] Manickam, P., Shankar, K., Perumal, E., Ilayaraja, M. and Sathesh Kumar, K., 2019. Secure data transmission through reliable vehicles in VANET using optimal lightweight cryptography. Cybersecurity and Secure Information Systems, pp.193-204. DOI: 10.1007/978-3-030-16837-7_9
[11] Yousefpoor, E., Barati, H. and Barati, A., 2021. A hierarchical secure data aggregation method using the dragonfly algorithm in wireless sensor networks. Peer-to-Peer Networking and Applications, 14(4), pp.1917-1942. DOI: 10.1007/s12083-020-01016-6
[12] Wan, Z., Liu, S., Ni, W. and Xu, Z., 2019. An energy-efficient multi-level adaptive clustering routing algorithm for underwater wireless sensor networks. Cluster Computing, 22, pp.14651-14660. DOI: 10.1007/s10586-018-2401-7
[13] Khisa, S. and Moh, S., 2021. Survey on recent advancements in energy-efficient routing protocols for underwater wireless sensor networks. IEEE Access, 9, pp.55045-55062. DOI: 10.1109/ACCESS.2021.3071516
[14] Ahmad, I., Rahman, T., Zeb, A., Khan, I., Othman, M.T.B. and Hamam, H., 2022. Cooperative energy-efficient routing protocol for underwater wireless sensor networks. Sensors, 22(18), p.6945. DOI: 10.3390/s22186945
[15] Luo, H., Xie, X., Han, G., Ruby, R., Hong, F. and Liang, Y., 2019. Multimodal acoustic-RF adaptive routing protocols for underwater wireless sensor networks. IEEE Access, 7, pp.134954-134967. DOI: 10.1109/ACCESS.2019.2941687
[16] Urooj, S., Lata, S., Ahmad, S., Mehfuz, S. and Kalathil, S., 2023. Cryptographic data security for reliable wireless sensor network. Alexandria Engineering Journal, 72, pp.37-50. DOI: 10.1016/j.aej.2023.03.073
[17] Harbi, Y., Aliouat, Z., Refoufi, A., Harous, S. and Bentaleb, A., 2019. Enhanced authentication and key management scheme for securing data transmission in the internet of things. Ad Hoc Networks, 94, p.101948. DOI: 10.1016/j.adhoc.2019.101948
[18] Babaeer, H.A. and Al-Ahmadi, S.A., 2020. Efficient and secure data transmission and sinkhole detection in a multi-clustering wireless sensor network based on homomorphic encryption and watermarking. IEEE Access, 8, pp.92098-92109. DOI: 10.1109/ACCESS.2020.2994565
[19] Haseeb, K., Almustafa, K.M., Jan, Z., Saba, T. and Tariq, U., 2020. Secure and energy-aware heuristic routing protocol for wireless sensor network. IEEE Access, 8, pp.163962-163974. DOI: 10.1109/ACCESS.2020.3021829
[20] Gomathi, S. and Gopala Krishnan, C., 2020. Malicious node detection in wireless sensor networks using an efficient secure data aggregation protocol. Wireless Personal Communications, 113(4), pp.1775-1790. DOI: 10.1007/s11277-020-07300-9