Mitigation

AML.M0021Generative AI Guidelines

What it is

Guidelines are safety controls that are placed between user-provided input and a generative AI model to help direct the model to produce desired outputs and prevent undesired outputs. Guidelines can be implemented as instructions appended to all user prompts or as part of the instructions in the system prompt. They can define the goal(s), role, and voice of the system, as well as outline safety and security parameters.

References

  1. https://atlas.mitre.org/mitigations/AML.M0021

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

ATLAS mitigation
Generative AI Guardrails
ATLAS mitigation
Generative AI Model Alignment
ATLAS mitigation
Restrict AI Agent Tool Invocation on Untrusted Data
ATLAS mitigation
Adversarial Input Detection
ATLAS mitigation
Input and Output Validation for AI Agent Components
ATLAS mitigation
Human In-the-Loop for AI Agent Actions
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.