SubTechniqueai-attack-stagingATLAS

AML.T0043.003Manual Modification

What it is

Adversaries may manually modify the input data to craft adversarial data. They may use their knowledge of the target model to modify parts of the data they suspect helps the model in performing its task. The adversary may use trial and error until they are able to verify they have a working adversarial input.

References

  1. https://atlas.mitre.org/techniques/AML.T0043.003

Related by meaning· 6

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

ATLAS
Craft Adversarial Data
ATLAS
Manipulate AI Model
ATLAS mitigation
Model Hardening
ATLAS
Poison Training Data
ATLAS
Modify AI Agent Configuration
ATLAS
Erode AI Model Integrity
Sourced from MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Curated by Adam Lundqvist, SQUR.