CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness
This work addresses the problem of AI safety and robustness verification for researchers and developers, though it is incremental as it builds on existing verification tools and platforms.
The authors tackled the challenge of verifying AI system robustness and safety by developing CAISAR, an open-source platform that unifies verification problem definitions and orchestrates multiple state-of-the-art tools, aiming to reduce the burden in methodology selection and tool development.
We present CAISAR, an open-source platform under active development for the characterization of AI systems' robustness and safety. CAISAR provides a unified entry point for defining verification problems by using WhyML, the mature and expressive language of the Why3 verification platform. Moreover, CAISAR orchestrates and composes state-of-the-art machine learning verification tools which, individually, are not able to efficiently handle all problems but, collectively, can cover a growing number of properties. Our aim is to assist, on the one hand, the V\&V process by reducing the burden of choosing the methodology tailored to a given verification problem, and on the other hand the tools developers by factorizing useful features-visualization, report generation, property description-in one platform. CAISAR will soon be available at https://git.frama-c.com/pub/caisar.