Depth-tracked regulatory audit primitives for privacy-preserving AI audits with signed envelopes and TenSEAL CKKS support.

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.

AI governance audit system for healthcare decision models. Evaluates fairness (DPD/EOD), calibration, and robustness with NIST AI RMF-aligned reporting.

ML model that flags DonorsChoose classroom projects at highest risk of going unfunded, with a fairness audit across school poverty levels.

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

How much can you trust a fairness audit when protected labels go missing? Code and results for arXiv:2506.23033

Predictive Modelling for Personalised Long COVID Risk Assessment | MSc Data Analytics, DCU | Calibrated LR · SHAP · Fairness Audit · Streamlit