We are currently conducting research on the use of Quantum Generative Adversarial Networks (QGANs) in Micro Aerial Vehicles (MAVs) scenarios. In this paper, we have shown that the QGAN paradigm can be employed by an adversary to learn generating data that deceives the monitoring of a Cyber-Physical System (CPS) and to perpetrate a covert attack. As a test case, the ideas are elaborated considering the navigation data of a MAV. A concrete QGAN design is proposed to generate fake MAC navigation data. Initially, the adversary is entirely ignorant about the dynamics of the CPS, the strength of the approach from the point of view of the bad guy. A design is also proposed to discriminate between genuine and fake MAV navigation data. The designs combine classical optimization, qubit quantum computing and photonic quantum computing. Using the PennyLane software simulation, they are evaluated over a classical computing platform. We assess the learning time and accuracy of the navigation data generator and discriminator versus space complexity, i.e., the amount of quantum memory needed to solve the problem. Our research work is being conducted using numeric and network simulations, as well as testbed and lab facilities to explore the complexity and impact of each of those communication models in terms of swarm intelligence.
Related Media