Skip to main content

Ctrl+K

Trusted AI Cookbook

Designing Trust

Design Process of a Trusted AI
Responsible Innovation
Extending AI Failure Modes: From Algorithm to Governance
Design Patterns for Testing and Monitoring
Fairness Metadata Management Flow
Links to Ubiquitous Computing

Assurance and Verification

Assurance Mechanisms
Useful Recipes during Assurance Lifecycle
Continuous Safety Monitoring
Recording Assurance Process Decisions
AI Roles

DevOps Integration

Continuous Delivery of Safe AI
Fairness Reporting
System Transparency Artefacts
Structuring the Codebase and Team Responsibilities

Characteristics of Trust

Trustworthiness: Key Components
Fairness Notions and Metrics
Bias Types in ML Pipeline
Mitigating Bias
Red Teaming

Data Practices

Tracking Data Operations
Exploring Participatory Data Governance
The ODI’s Data Taxonomy

Use Case: Finance

Fairness of Large Language Models in Finance
A Practical Review of Financial Large Language Models
Evaluating and Mitigating Fairness in Financial Services: A Human-AI Interaction Perspective
Interpretability tools for improving fairness and equity
Reading List: LLMs in Finance - UK Context

Use Case: Biometrics

Fairness in Face Biometrics

References

References

Repository
Open issue

Index

By Alpay Sabuncuoglu

© Copyright 2024.