SubTechniquediscoveryATLAS

AML.T0069.002System Prompt

What it is

Adversaries may discover a large language model's system instructions provided by the AI system builder to learn about the system's capabilities and circumvent its guardrails.

References

  1. https://atlas.mitre.org/techniques/AML.T0069.002

Related by meaning· 6

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

ATLAS
Extract LLM System Prompt
ATLAS
Discover LLM System Information
ATLAS
LLM Prompt Crafting
ATLAS
LLM Prompt Injection
ATLAS
LLM Prompt Self-Replication
ATLAS
LLM Prompt Obfuscation
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.