LAUSR

This work investigates the proactive eavesdropping through a friendly full-duplex (FD) relay and a legitimate monitor over the wireless-powered suspicious communication network, where one suspect source performs energy harvesting (EH) from one dedicated power beacon and then communicates with one suspect destination. Under this setup, a relay-aided proactive eavesdropping scheme is designed to improve the surveillance performance of the system. The closed-form expressions are derived under linear and nonlinear EH models, including the decoding outage probability for the suspicious link, the eavesdropping outage probability for the eavesdropping link, and the average eavesdropping rate (AER). Based on these obtained expressions, an optimization problem to maximize the AER is formulated by jointly optimizing the power and location of the relay. The existence of the optimal solution is carefully analyzed. Moreover, the separate optimization issues of the power and location are first established, and then a bisection-based searching algorithm is presented for the joint optimization problem with the linear EH model. Furthermore, to reduce the complexity of joint optimization, a low-complexity learning-based iteration algorithm is further proposed by employing the well-fitting characteristic of the deep feedforward neural network. Numerical results verify the effectiveness of the proposed algorithm, and show that the optimized FD relay-aided proactive eavesdropping scheme outperforms the reference schemes. Finally, the application scenarios of the proposed proactive eavesdropping scheme are discussed.