6G -enabled qubit-based concealed communication with AI-driven breach detection in autonomous fleets

Autonomous Vehicles (AVs) rely on secure neighbors and proactive infrastructures for robust communications. The heterogeneous communication scenario exploits concealed media for secure information exchange. Concealed communications assist precise navigation, information exchange, object detection, etc. In this process, the end-to-end computations are complex in converting a vehicle communication stream to an encrypted stream. This article introduces a Secure Module for Concealed Navigation Communication (SM-CNC) in AV environments. The information identified is transmitted by attaching volatile authentication that disintegrates if a communication source (vehicle or access point, etc.) is intercepted. Contrarily, the information is dropped in the communication medium if adverse or unauthorized vehicles intercept. This process is monitored during the relaying and end-to-end validation processes. The proposed secure module relies on quantum computing and recurrent learning for multiple recommendations from the information relay points. The information points are modeled as qubits for low-complex processing to administer security and ensure reliable communication. This prevents security breaches in the concealed medium through authentication failures and unauthorized access detection based on vehicle information allocated to individual qubits. The learning paradigm analyzes the qubits for their availability for secure information exchange throughout the navigation. The performance of the proposed module is verified using the metrics of communication failure, complexity, and authentication rate. The proposed secure module improves the authentication rate by 9.29% and reduces the communication failure and computation complexity by 11.87% and 12.13% respectively, for the maximum communication requests/ interval.