Out-of-distribution robustness

https://taxonomy.eticas.ai/risk/out-of-distribution-robustness

Maturity: emerging

Unpredictable behaviour or failure when the system is exposed to inputs outside the distribution of its training data.

This subcategory is emerging. It has not yet been validated through established assessment methods.

System type: ADM and LLM systems
Lifecycle stages: In Processing, Post Processing

Mappings to external frameworks

Framework	Reference
NIST AI Risk Management Framework (AI 100-1)	Valid & Reliable (robustness to distribution shift)

Framework	Reference
MIT AI Risk Repository	Lack of capability or robustness

Source: HRA project taxonomy

Part of the Eticas AI Risk Taxonomy. URI: https://taxonomy.eticas.ai/risk/out-of-distribution-robustness