Statement 28: Test for safety, robustness, and reliability

Agencies must

  • Criterion 101: Test the computational performance of the system.

    This includes:

    • testing for response times, latency, and resource usage under various loads
    • network and hardware load testing.
  • Criterion 102: Test safety measures through negative testing methods, failure testing, and fault injection.

    This includes:

    • testing for incorrect or harmful inputs.
  • Criterion 103: Test reliability of the AI output, through stress testing over an extended period, simulating edge cases, and operating under extreme conditions. 

Agencies should

  • Criterion 104: Undertake adversarial testing (red team testing), attempting to break security and privacy measures to identify weaknesses.

    AI-specific attacks can be executed before, during, and after training.

    Examples of attacks that can be made before and during training includes: 

    • dataset poisoning
    • algorithm poisoning
    • model poisoning
    • backdoor attacks. 

    Examples of attacks that can be made after training includes: 

    • input attack and evasion
    • reverse engineering the model and data.
       

Statement 29: Test for conformance and compliance

Connect with the digital community

Share, build or learn digital experience and skills with training and events, and collaborate with peers across government.