paper-with-me

홈 › Papers

CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness

2022-06-07 · Julien Girard-Satabin, Michele Alberti, François Bobot, Zakaria Chihani, Augustin Lemesle

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.

📄 PDF Abstract BibTeX arXiv:2206.03044

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The CAISAR Platform: Extending the Reach of Machine Learning Specification and Verification

2025-06-10 · Michele Alberti, François Bobot, Julien Girard-Satabin, Alban Grastien 외

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?

2025-07-03 · Joseph Boland arxiv

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

2021-02-24 · Lana Sinapayen

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 Life

Games for Artificial Intelligence Research: A Review and Perspectives

2023-04-26 · Chengpeng Hu, Yunlong Zhao, Ziqi Wang, Haocheng Du 외

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 MakingScheduling

A cross-regional review of AI safety regulations in the commercial aviation

2025-02-12 · Penny A. Barr, Sohel M. Imroz

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…