SubTechniqueexecutionATLAS

AML.T0051.000Direct

What it is

An adversary may inject prompts directly as a user of the LLM. This type of injection may be used by the adversary to gain a foothold in the system or to misuse the LLM itself, as for example to generate harmful content.

References

  1. https://atlas.mitre.org/techniques/AML.T0051.000

Related by meaning· 6

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

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