LogoLogo
  • Getting Started
  • 🔍Taxonomy
    • Introduction
    • Effect (SEP) View
      • Security
      • Ethics
      • Performance
    • Lifecycle View
    • Schema
  • 📦Database
    • Introduction
    • Framework
      • Base Classes
      • Auxiliary Classes
    • 🛠️Backend
    • 🛠️Editorial Interface
  • 👷‍♀️Developer Tools
    • Python SDK
      • Datamodels
      • Connectors
      • 🛠️Integrations
        • garak
        • ModsysML (Apollo)
        • 🐢Giskard
        • Inspect AI
      • API Reference
Powered by GitBook
On this page
  1. Taxonomy

Introduction

PreviousGetting StartedNextEffect (SEP) View

Last updated 1 month ago

The AVID taxonomy is intended to serve as a common foundation for AI/ML/data sciemce, product, and policy teams to manage potential risks at different stages of a ML workflow. In spirit, this taxonomy is analogous to for cybersecurity vulnerabilities, and for adversarial attacks on ML systems.

At a high level, the current AVID taxonomy consists of two views, intended to facilitate the work of two different user personas.

  • : for the auditor persona aiming to assess risks for a ML system of components of it.

  • : for the developer persona aiming to build an end-to-end ML system while being cognizant of potential risks.

Based on case-specific needs, people involved with building a ML system may need to operate as either of the above personas.

For machine-readability, taxonomies are shared using the standardized format. This also allows us to support additional taxonomies. See to learn more.

🔍
MITRE ATT&CK
MITRE ATLAS
Effect view
Lifecycle view
MISP
Schema