Depth-tracked regulatory audit primitives for privacy-preserving AI audits with signed envelopes and TenSEAL CKKS support.
-
Updated
May 25, 2026 - Python
Depth-tracked regulatory audit primitives for privacy-preserving AI audits with signed envelopes and TenSEAL CKKS support.
AI governance audit system for healthcare decision models. Evaluates fairness (DPD/EOD), calibration, and robustness with NIST AI RMF-aligned reporting.
PhD-level, investor-friendly interactive M&A visualization platform tracking women's health acquisitions, FemTech exits, digital health deal flow, and strategic buyer networks. D3.js network graphs, valuation matrices, and temporal deal analytics.
Practical playbooks for AI/ML teams to detect and correct bias, assessment, root cause analysis, fairness metrics, and pre/in/post-processing interventions. Covers classical ML with EU AI Act, GDPR, ECOA, and HIPAA references.
Fairness audit of Detoxify's toxicity classifier on Civil Comments quantifying demographic bias via FPR disparity, subgroup AUC, counterfactual analysis, and intersectionality, with threshold-optimization mitigation
Add a description, image, and links to the fairness-audit topic page so that developers can more easily learn about it.
To associate your repository with the fairness-audit topic, visit your repo's landing page and select "manage topics."