Authors:
Suman Avdhesh Yadav, Pinki Sharma, Rahat Naz, Pramod Kumar Sagar, Birendra Kumar Saraswat, Angeles Quezada

Addresses:
School of Computer Science and Engineering, IILM University, Gautam Buddha Nagar, Uttar Pradesh, India. Department of Computer Applications, JSS Academy of Technical Education, Gautam Buddha Nagar, Uttar Pradesh, India. National School of Computer Science, University of Petroleum and Energy Studies, Dehradun, Uttarakhand, India. Department of Computer Science and Engineering, Raj Kumar Goel Institute of Technology, Ghaziabad, Uttar Pradesh, India. Department of Information Technology, GL Bajaj Institute of Technology and Management, Gautam Buddha Nagar, Uttar Pradesh, India. Department of Systems and Computing, Institute of Tijuana, Tijuana, Baja California, Mexico.

Abstract:

Wireless Sensor Networks (WSNs) have been widely applied across various sectors, leading to a vast increase in the transmission of sensitive data in these networks. Hence, the security of traffic in this concentration of wireless sensor networks has become an imperative problem. Traditional security measures failed to provide sufficient security in WSN environments; researchers have proposed alternatives. To handle the significant traffic in D2D high-density WSNs, researchers propose a deep learning-based security architecture. The multi-branch deep learning architecture proposed in this work is a major gateway for this industry, identifying different types of sensitive traffic in content and behaviour. The proposed model obtained 83.94% energy consumption, 80.95% data confidentiality, 89.95% scalability and 92.97% Communication overhead. This approach is better than the more conventional approaches at identifying sensitive messages and prioritising them. It relies on a routing trick that uses the network's real-time state to reroute critical data along alternative paths. This is intended to preserve the privacy of private data by minimising the likelihood of theft or loss. It allows the network to recognise and discount malignant antipodes that act to pervert the network or halt the private data transaction. There is also a recommendation for an artificial intelligence intrusion detection system capable of learning new attack patterns and adapting its defence to them.

Keywords: High-Density; Encryption and Authentication; Access Control; Network Traffic; Sensitive Data; Data Transaction; Intrusion Detection System; WSN Environments.

Received on: 16/02/2025, Revised on: 01/05/2025, Accepted on: 14/06/2025, Published on: 03/01/2026

DOI: 10.69888/FTSCL.2026.000596

FMDB Transactions on Sustainable Computer Letters, 2026 Vol. 4 No. 1, Pages: 1–13

• Views : 83
• Downloads : 12

Download PDF