CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The CAISAR Platform: Extending the Reach of Machine Learning Specification and Verification
The formal specification and verification of machine learning programs saw remarkable progress in less than a decade, leading to a profusion of tools. However, diversity may lead to fragmentation, resulting in tools that…
Moral Responsibility or Obedience: What Do We Want from AI?
As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming…
Perspective: Purposeful Failure in Artificial Life and Artificial Intelligence
Complex systems fail. I argue that failures can be a blueprint characterizing living organisms and biological intelligence, a control mechanism to increase complexity in evolutionary simulations, and an alternative to cl…
Artificial LifeGames for Artificial Intelligence Research: A Review and Perspectives
Games have been the perfect test-beds for artificial intelligence research for the characteristics that widely exist in real-world scenarios. Learning and optimisation, decision making in dynamic and uncertain environmen…
Decision MakingSchedulingA cross-regional review of AI safety regulations in the commercial aviation
In this paper we examine the existing artificial intelligence (AI) policy documents in aviation for the following three regions: the United States, European Union, and China. The aviation industry has always been a first…