Advanced Source Privacy: DQ-NN and Phantom Routing in IoT-Integrated Multiple-Source and Destination Wireless Sensor Networks

Internet of Things (IoT) and Wireless Sensor Networks (WSNs) have brought about revolutionary opportunities for many areas, they have also raised serious security issues, especially with relation to source node location privacy in IoT-enabled WSNs. In response, we put out a brand-new hybrid Deep Q-learning Neural Network (DQ-NN) strategy designed specifically for Source Location Privacy (SLP) in Internet of Things (IoT)-enabled WSNs that use phantom routing. Through the strategic selection of phantom nodes, our method establishes various routing paths from source to sink nodes via these phantoms, taking into account factors such as neighbour lists, energy levels, distances, and trust heterogeneity. The use of DQ-NN, a combination of Deep Q-learning Network (DQN) and Deep Neural Network (DNN), is essential to our approach since it guarantees source node location privacy protection in addition to effective and reliable data transfer through IoT-enabled WSNs, strengthening the privacy and security environment of IoT networks and facilitating easy integration with everyday life. The suggested DQ-NN performs better than other current methods.