Sven Hallerbach

This work proposes a novel approach under the more realistic black-box threat model that utilizes concepts from reinforcement learning to optimize perturbations with a non-differentiable target model, and shows the success of reinforcement learning inspired black-box adversarial attack (RIBA) in generating adversarial perturbations using only a small number of queries to the target model.

Safety Nets can shrink AI system sizes by three orders of magnitude while guaranteeing 100% correct outputs, making them a game-changer for certifying AI in aviation.

Guaranteeing complete coverage of an AI system's operational domain in high-dimensional spaces is now possible, paving the way for safer AI deployment in aviation and other safety-critical applications.