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
  • Vulnerability
  • Report
  1. Database
  2. Framework

Base Classes

PreviousFrameworkNextAuxiliary Classes

Last updated 1 year ago

Vulnerability

Vulnerabilities are linked to the taxonomy through multiple tags, denoting the AI risk domains (Security, Ethics, Performance) this vulnerability pertains to, (sub)categories under that domain, as well as AI lifecycle stages. A vulnerability in AVID can pertain to one or more of the three levels: Dataset, Model, or System.

Report

Reports are occurrences of a vulnerability. Based on the references provided in a specific report, reports can potentially more granular and reproducible than vulnerabilities. We classify reports in four types, in increasing degree of quantitative evidence:

  1. Issue: qualitative evaluation based on a single sample or handful of samples,

  2. Advisory: qualitative evaluation based on multiple Incidents,

  3. Measurement: quantitative evaluation with associated data and metric,

  4. Detection: A Measurement deemed critical by a threshold or statistical test.

These types are reminiscent of the , and accommodate diverse AI evaluation scenarios from the user perspective.

📦
three levels of AI Auditing