Agentic AI Reference Architecture

Governance & Compliance · Software component

Differentially Private Fairness Auditor

Software componentGovernance & ComplianceSafety, Security & Governancearc:DifferentiallyPrivateFairnessAuditor

A privacy-preserving fairness auditor that adds calibrated noise to demographic counts and fairness metrics under a tunable privacy budget (epsilon).

Responsibility. Publishes noisy aggregate fairness metrics with differential privacy guarantees.

Variant of Privacy-Preserving Fairness Auditor abstract

When to choose. Choose when fairness metrics must be released with provable guarantees that no individual's participation or outcome can be inferred, and sample sizes are large enough to tolerate added noise.

specializesalternative toalternative toPrivacy-Preserving Fairness Auditor: specializesPrivacy-Preserving Fairn…Federated Fairness Auditor: alternative toFederated Fairness AuditorSecure Multiparty Fairness Auditor: alternative toSecure Multiparty Fairne…
Direct neighbourhood (hover for relationship types)

Relationships

alternative to variability

Design guidance

Classification

Patterns
Differential privacy

Sources

  1. Ch9.4: T. Nguyen, "Fairness and Bias Mitigation," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.4. ISBN: 9798244538229.
  2. Ref9.02: "Responsible AI and Ethical Principles," unpublished reference note (02-Responsible-AI-Ethical-Principles.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note