Catalogue of Tools & Metrics for Trustworthy AI

These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.

FLARE-AI



FLARE-AI is an open-source AI flaw and incident reporting tool that aims to address fragmentation in the AI flaw reporting ecosystem, where researchers are often uncertain where to submit reports and recipient organisations rarely share reports with other relevant stakeholders. 

The tool allows AI actors, including researchers, red teamers, affected users, developers, to document a vulnerability, bias, or incident through a single submission process. Reports are structured using established taxonomies, including the AIAAIC harm taxonomy and the OWASP Top 10 for LLMs, and are generated in a machine-readable JSON-LD format. This format can be automatically converted into schemas used by other systems, such as CSAF for security coordination or the formats used by AI incident and vulnerability databases.  

The source code is published under an MIT license and consists of a Next.js frontend and a Strapi CMS backend, with integration support for CERT/VINCE and Hugging Face Hub. Publishing the full codebase allows organisations to self-host, review, or adapt the reporting pipeline according to their requirements. 

Use Cases

There is no use cases for this tool yet.

Would you like to submit a use case for this tool?

If you have used this tool, we would love to know more about your experience.

Add use case
Partnership on AI

Disclaimer: The tools and metrics featured herein are solely those of the originating authors and are not vetted or endorsed by the OECD or its member countries. The Organisation cannot be held responsible for possible issues resulting from the posting of links to third parties' tools and metrics on this catalogue. More on the methodology can be found at https://oecd.ai/catalogue/faq.