Towards Quantum Enhanced Adversarial Robustness In Machine Learning

Recent work has employed quantum-mechanical phenomena to defend against adversarial attacks in machine learning, spurring the development of the field of quantum adversarial machine learning (QAML). Despite promising early results, there remain challenges in building robust real-world QAML tools. This Perspective discusses recent progress in QAML and identifies key challenges, as well as suggesting future research directions that could determine the route to practicality for QAML approaches.