A Shapley Value Estimation Speedup for Efficient Explainable Quantum AI

This work focuses on developing efficient post-hoc explanations for quantum AI algorithms. In classical contexts, the cooperative game theory concept of the Shapley value adapts naturally to post-hoc explanations, where it can be used to identify which factors are important in an AI's decision-making process. An interesting question is how to translate Shapley values to the quantum setting and whether quantum effects could be used to accelerate their calculation. We propose quantum algorithms that can extract Shapley values within some confidence interval. Our method is capable of quadratically outperforming classical Monte Carlo approaches to approximating Shapley values up to polylogarithmic factors in various circumstances. We demonstrate the validity of our approach empirically with specific voting games and provide rigorous proofs of performance for general cooperative games.

Faking and Discriminating the Navigation Data of a Micro Aerial Vehicle Using Quantum Generative Adversarial Networks

We show that the Quantum Generative Adversarial Network (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 Micro Aerial Vehicle (MAV). A concrete QGAN design is proposed to generate fake MAV 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.

Quality Amplification of Error Prone Navigation for Swarms of Micro Aerial Vehicles (with Detailed Simulations)

We present an error tolerant path planning algorithm for Micro Aerial Vehicles (MAV) swarms. We assume a MAV navigation system without relying on GPS-like techniques. The MAV find their navigation path by using their sensors and cameras, in order to identify and follow a series of visual landmarks. The visual landmarks lead the MAV towards the target destination. MAVs are assumed to be unaware of the terrain and locations of the landmarks. Landmarks are also assumed to hold a-priori information, whose interpretation (by the MAVs) is prone to errors. We distinguish two types of errors, namely, recognition and advice. Recognition errors are due to misinterpretation of sensed data and a-priori information or confusion of objects (e.g., due to faulty sensors). Advice errors are due to outdated or wrong information associated to the landmarks (e.g., due to weather conditions). Our path planning algorithm proposes swarm cooperation. MAVs communicate and exchange information wirelessly, to minimize the {\em recognition} and {\em advice} error ratios. By doing this, the navigation system experiences a quality amplification in terms of error reduction. As a result, our solution successfully provides an adaptive error tolerant navigation system. Quality amplification is parametetrized with regard to the number of MAVs. We validate our approach with theoretical proofs and numeric simulations.