SubTechniquedefense-evasionATLAS

AML.T0067.000Citations

What it is

Adversaries may manipulate the citations provided in an AI system's response, in order to make it appear trustworthy. Variants include citing a providing the wrong citation, making up a new citation, or providing the right citation but for adversary-provided data.

References

  1. https://atlas.mitre.org/techniques/AML.T0067.000

Related by meaning· 6

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

ATLAS
LLM Trusted Output Components Manipulation
ATLAS
LLM Prompt Crafting
ATLAS
LLM Prompt Obfuscation
ATLAS
Impersonation
ATLAS
LLM Data Leakage
ATLAS
False RAG Entry Injection
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.