EUVIMEDEUVIMED entdecken
Crossref

CNN-Based Intelligent Intrusion Detection for Secure Routing in IoT-Enabled Wireless Sensor Networks

Dipal Khandelwal, Dr. Vaishali Gupta, Mr. Ved Kumar Gupta

International Journal of Drug Delivery Technology · 25.05.2026 · 16 (32s)

DOI: 10.25258/ijddt.16.32s.73 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 25.05.2026. Verfasst von Dipal Khandelwal und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

New concerns about network security and communication quality have arisen as a result of the rapid expansion of the Internet of Things (IoT), which has greatly aided the notion of Wireless Sensor Networks (WSN) in many areas of life. Due to their resource constraints and the use of multi-hop routing, IoT-enabled WSNs are particularly vulnerable to routing-based attacks such as sinkhole, probe, and denial-of-service (DoS). These attacks can have a devastating effect on the network's performance and integrity and greatly jeopardize data integrity. Current intrusion detection systems (IDS) can be characterized as limited to complex and changing attack patterns because they are usually based on manual feature engineering, coupled with routing-blind analysis. In order to address these issues, this study will propose a Convolutional Neural Network (CNN)–based IDS that uses deep learning (DL) to implement safe routing in WSNs that incorporate IoT technologies. We can examine the network activity comprehensively using the recommended model, which combines features of the network level and routing specificities. These features include hop count, node energy, rate of packets, delay, and rate of packet drop. An actual dataset is created and pre-processed based on feature scaling and label encoding methods to achieve the best model performance. The suggested model achieves high values of recall, F1-score, precision, and classification rate (about 97.5%), according to the experimental evaluation data. Results from the confusion matrix, ROC curves, and precision recall metrics show that the model performs well and can be generalized, lending credence to the model's performance analysis in multi-class intrusion detection. Combining routing-aware algorithms with DL can boost detection accuracy, according to the findings. The results suggest that the suggested solution represents an efficient, scalable, and reliable IDS to the IoT-enabled WSNs, which are relevant to enhanced secure routing and resilience in the networks. This research highlights the possibilities of the smart data-driven models in meeting the future cybersecurity issues in the current IoT infrastructures.

Zitieren

APA

Khandelwal, D., Gupta, D. V., & Gupta, M. V. K. (2026). CNN-Based Intelligent Intrusion Detection for Secure Routing in IoT-Enabled Wireless Sensor Networks. International Journal of Drug Delivery Technology, 16(32s). https://doi.org/10.25258/ijddt.16.32s.73

Vancouver

Khandelwal D, Gupta DV, Gupta MVK. CNN-Based Intelligent Intrusion Detection for Secure Routing in IoT-Enabled Wireless Sensor Networks. International Journal of Drug Delivery Technology. 2026;16(32s). doi:10.25258/ijddt.16.32s.73

BibTeX
@article{Khandelwal2026,
  author = {Khandelwal, Dipal and Gupta, Dr. Vaishali and Gupta, Mr. Ved Kumar},
  title = {CNN-Based Intelligent Intrusion Detection for Secure Routing in IoT-Enabled Wireless Sensor Networks},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {32s},
  doi = {10.25258/ijddt.16.32s.73}
}
Kostenlos starten →