# A.9 Robustness

AI-related objective: The AI system keeps performing as intended under perturbation, unexpected input, distribution shift and adversarial conditions, and degrades in a controlled way. Used when establishing risk criteria (6.3.4), identifying consequences (6.4.2.6) and evaluating risk (6.4.4). The artefact behind the answer is robustness test results. Read robustness against the objective the use threatens most.

- Framework: ISO/IEC 23894:2023
- Cited to: ISO/IEC 23894:2023, clause A.9
- Source: https://www.iso.org/standard/77304.html
- Last updated: 2026-10-20

## What it asks

AI-related objective: The AI system keeps performing as intended under perturbation, unexpected input, distribution shift and adversarial conditions, and degrades in a controlled way. Used when establishing risk criteria (6.3.4), identifying consequences (6.4.2.6) and evaluating risk (6.4.4).

## Where generative AI changes the answer

Robustness is tested by an input designed to break the system, not by the demo that was built to show it working.

## Who it binds

The AI risk owner, with the objective owner named in the risk treatment plan.

## Evidence an auditor samples

- Robustness test results

## The test you can run

Ask which objective the use threatens most and what measure shows it. A blank answer is the finding.

## Common failures

- Performance measured on clean test data only

## Before the draft publishes

Pick the two objectives the use most affects, write the test you would apply, and record the result before the draft is published.

## What this page does not say

It does not state the text of ISO/IEC DTS 25568, because ISO has not published the draft's clause text. It does not certify anything.

Not legal advice; does not certify.