What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
This work tackles the problem of ensuring safety in AI systems for critical applications, but it appears incremental as it builds on existing verification approaches.
The paper addresses the challenge of achieving provable safety guarantees for learning-enabled systems in safety-critical domains, proposing a two-step verification method to attain provable statistical guarantees.
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving safety guarantees is one of the most prominent. In this paper, we first discuss the engineering and research challenges associated with the design and verification of such systems. Then, based on the observation that existing works cannot actually achieve provable guarantees, we promote a two-step verification method for the ultimate achievement of provable statistical guarantees.