Fairness
Fairness in the context of production machine-learning systems.
Lessons
Formal explanations, examples, simulations, and checkpoints.
Inventory, risk tiers, accountability, evidence
Governance starts by giving the complete decision system a scope, an owner, a risk tier, and versioned evidence.
Governance, fairness, privacy & securityFairness definitions, slices, thresholds, tradeoffs
Fairness work makes the chosen harm, comparison, uncertainty, and policy tradeoff explicit for every affected slice.
Governance, fairness, privacy & securityPrivacy minimization, retention, federated learning, DP
Privacy engineering reduces what the entire system can learn and retain about one protected unit over time.
Governance, fairness, privacy & securityPoisoning, evasion, extraction, and LLM threats
Models can propose; trusted code, identity, and policy must decide what the system is allowed to read, change, or reveal.
Governance, fairness, privacy & securityRed teams, human oversight, audit, and response
Assurance is credible when adversarial testing, human intervention, auditability, and recovery are exercised against the exact system being released.
Courses & assignments
Dependency-authoritative learning units.
Casebook
Reported facts and course reconstructions.
Auditing and retiring an image-cropping algorithm
Sometimes product redesign and user agency are stronger mitigations than model tuning.
LinkedIn · Fairness, privacy & securityA fairness toolkit for large-scale AI
Fairness infrastructure must be context-aware, governed, and integrated into decisions.
Stripe · Fairness, privacy & securityStripe Radar: learning fraud under adversarial pressure
Risk modeling connects delayed supervision, adversarial drift, calibrated decisions, and layered controls.