← All domains

Safety & Responsible AIView domain

APRF-25

Safety & Responsible AI

Prevent harmful content and unfair outcomes—NIST trustworthiness beyond adversarial security.

Purpose

Define and enforce content-safety, harm-prevention, fairness/bias, and user-facing AI disclosure requirements appropriate to the product domain and risk tier.

Engineering philosophy

Safety is not a synonym for security. Adversarial controls stop attackers; safety controls stop harmful or unfair outcomes for users and society. Both are required for production readiness.

Why it matters

Systems can be “secure” yet produce toxic, discriminatory, or undisclosed AI-generated content that creates regulatory, brand, and user harm.

Common failures

  • No domain-specific harm taxonomy or refusal policy
  • Safety filters only on output, not on tool-mediated side effects
  • No fairness or disparity testing for high-stakes decisions
  • Users not informed when they interact with AI

Mandatory checks

Gate controls. Each check is pass/fail via artifact + pass condition. Expected from the annotated capability level when the system meets the minimum criticality tier.

  • SAF-M1L3 · DefinedTier 2 · Productionmanual

    A documented harm taxonomy and refusal/escalation policy shall exist for the product domain

    Artifact
    Approved harm taxonomy + refusal/escalation policy (versioned, owned)
    Pass condition
    Policy document has version, owner, and review date ≤ 12 months; maps ≥ domain-minimum harm categories with explicit refuse vs escalate actions for each
  • SAF-M2L3 · DefinedTier 2 · Productionautomated

    Automated safety evaluation gates shall run on relevant releases

    Artifact
    Safety suite definition with numeric thresholds + CI gate reports
    Pass condition
    Safety gate executed on 100% of in-scope releases in last 30 days; fail blocks promote unless time-boxed waiver (expiry ≤ 14 days) with owner
  • SAF-M3L3 · DefinedTier 2 · Productionhybrid

    Users shall be disclosed when interacting with AI where required by policy or law

    Artifact
    Disclosure UX inventory + screenshot/checklist audit of in-scope surfaces
    Pass condition
    AI-interaction disclosure present on 100% of in-scope user surfaces per policy checklist; 0 critical surfaces missing disclosure in the latest audit
  • SAF-M4L4 · Quantitatively ManagedTier 3 · Mission Criticalhybrid

    Fairness/disparity evaluation shall cover high-stakes decision paths

    Artifact
    Fairness/disparity eval methodology + latest run report for in-scope high-stakes paths
    Pass condition
    PASS if in-scope high-stakes paths are inventoried and the latest eval (≤90 days) is retained with thresholds and owners

Evidence required

  • Harm taxonomy and policy document
  • Safety eval suite definitions and recent gate results
  • Disclosure UX or policy evidence

Severity & risk

Severity
critical
Impact if violated
Risk level
high
Typical residual risk (impact × likelihood)

Engineering best practices

  • Separate safety eval datasets from adversarial security corpora
  • Fail closed on high-severity harm categories
  • Align safety thresholds to criticality tier, not headcount
  • Log safety refusals for measurement without storing unnecessary sensitive content

Automatic validations

  • CI safety-gate failures block release
  • Online monitoring of refusal rates and safety classifier signals
  • Regression tests for known harmful prompt classes

Manual validations

  • Domain expert review of harm taxonomy
  • Periodic calibration of automated safety graders vs human labels

Examples

  • A tutoring agent refuses self-harm content and escalates to a human protocol
  • A lending assistant reports group disparity metrics before each model promotion

References

Crosswalks

  • MEASURE Measure

    NIST AI Risk Management Framework · supports

  • Safe Safe

    NIST AI Risk Management Framework · aligns-with

  • Fair Fair — Harmful Bias Managed

    NIST AI Risk Management Framework · partial

  • §6 Planning

    ISO/IEC 42001 · partial

  • Annex A AI system controls (selected themes)

    ISO/IEC 42001 · partial

  • LLM05 Improper Output Handling

    OWASP Top 10 for Large Language Model Applications · supports

  • LLM09 Misinformation

    OWASP Top 10 for Large Language Model Applications · aligns-with

  • CC3 Risk Assessment

    SOC 2 Trust Services Criteria · evidence-for

  • Generative AI Lens Generative AI Lens (themes)

    AWS Well-Architected Framework · aligns-with

Future evolution

Shared harm taxonomies and portable safety scorecards across model providers.