Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
Vijil Docs
Logo
  • Setup
  • Quickstart Tutorial

Evaluating Agents

  • Introduction
  • Dimensions of Trust
    • Security
    • Privacy
    • Hallucination
    • Robustness
    • Toxicity
    • Stereotype
    • Fairness
    • Ethics
  • Abstractions
    • Harnesses
    • Scenarios
    • Probes
    • Detectors
  • Tutorials
    • Run your First Test
    • Working with Evaluations
    • Managing API keys
    • OWASP LLM Top 10
    • RAG metrics
    • Working with Detections
    • Create a Custom Harness
    • Evaluating Custom Agents
    • Evaluation Reports
  • Integrations
    • Google Vertex AI
    • DigitalOcean
    • AWS Bedrock
    • Custom Endpoints
    • Local LLMs and Agents
  • Glossary
    • Detector Glossary
    • Probe Glossary
  • API Reference

Protecting Agents

  • Introduction
  • Getting Started
  • Overview
  • Configuring Guardrails
  • List of Detection Methods
    • Security
    • Moderation
    • Privacy
    • Integrity
  • Tutorials
    • Using Guardrails
    • Applying Dome to Clients
    • Langchain Integration
    • Google ADK Integration
    • Custom Detectors
    • Observability
  • Integrations
Back to top
View this page

Dimensions of TrustΒΆ

Vijil evaluates LLM trustworthiness along 8 dimensions. For each dimension, we assess vulnerability to several attack vectors. Each attack vector is treated as one evaluation module. Each module contains one or more tests.

  • Security
  • Privacy
  • Hallucination
  • Robustness
  • Toxicity
  • Stereotype
  • Fairness
  • Ethics
Next
Security
Previous
Introduction
Copyright © 2024, Vijil Inc
Made with Sphinx and @pradyunsg's Furo