Explainability Platform Kaa

Kaa is a framework allowing to apply several methods and metrics from several dedicated libraries on AI model
to verify them.
It is built around a kernel offering a text interface ( textitText-based User Interface) and hosting two sets of
plugins:

• plugins of explainability libraries called pluginsXAI
• the plugins of the textitvs explicability checkboxes called pluginsUCXAI

In this version of Kaa, the AIX360, Alibi, Captum, PAIR saliency, Shap and Xplique plugins are provided

Documentation

User Manual

User manual is available for download here.

Version 24.05.14 has only been tested on Ubuntu 20.04 and might not work on a Windows environment.

Methodological Guidelines

• Methodological Guideline for Explainability

Scientific Contribution

• Comments on ISO 6254 (Explainability)

Benchmark

• Explicability benchmark

Application over use-case

• Unsupervised Anomaly Detection and Explainability tools for Time Series

State of the Art

• Characterization of the notion of trust

Demonstrator

A demonstrator based on public use-cases is available here.

A demonstrator based on private use-cases is available here.

Support

Support for Kaa  must be obtained by sending an email to support@confiance.ai

Ensure your email contains :

• Your name
• A link to this page
• the version you are working with
• A clear description of the problematic (bug, crash, feature or help request)
• A full description of the problem whichallow to reproduce it
• Any file or screenshort element mandatory for the full understanding of the problematic