Techniqueresource-developmentATLAS

AML.T0065LLM Prompt Crafting

What it is

Adversaries may use their acquired knowledge of the target generative AI system to craft prompts that bypass its defenses and allow malicious instructions to be executed. The adversary may iterate on the prompt to ensure that it works as-intended consistently.

References

  1. https://atlas.mitre.org/techniques/AML.T0065

Related by meaning· 6

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

ATLAS
LLM Prompt Injection
ATLAS
LLM Prompt Obfuscation
ATLAS
LLM Prompt Self-Replication
ATLAS
Extract LLM System Prompt
ATLAS
LLM Data Leakage
ATLAS
LLM Trusted Output Components Manipulation
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.