Joint Computation Offloading and Resource Allocation in Covert VEC Networks

Covert communication can provide higher security by protecting communication behavior. In this paper, we utilize covert communication to protect the communication behavior in vehicular edge computing (VEC) networks, that is covert VEC networks, where multiple task vehicles (TVs) secretly initiate the transmission of sensitive tasks without being detected by attacker Willie. Specifically, TVs offload tasks to the neighboring roadside unit (RSU) subject to their limited abilities. Meanwhile, RSU transmits artificial noise to against Willie's eavesdropping attack. Then, we consider an optimization problem for joint computing offloading and resource allocation of the covert VEC networks conceived. A soft actor-critic (SAC)-based algorithm is proposed for minimizing total latency under given covert constraints in computation offloading and resource allocation. Simulation results demonstrate the superior performance of our proposed algorithm compared to similar benchmarks, which explores the possibility of achieving covert transmission in VEC networks.