Introduction to trusted AI. Learn to use fairness algorithms to reduce and mitigate bias in data and models with aif360 and explain models with aix360

GBDF: Gender Balanced DeepFake Dataset

Algorithmic inspection for trustworthy ML models

Sample project using IBM's AI Fairness 360 is an open source toolkit for determining, examining, and mitigating discrimination and bias in machine learning (ML) models throughout the AI application lifecycle.

🎯 EquiLens - AI Bias Detection Platform for LLMs via Ollama. Interactive CLI with corpus generation, multi-metric auditing, statistical analysis & visualization. Features enhanced auditors, dynamic concurrency, resume capability & rich progress tracking. Alt Links: https://equilens.pages.dev/ , https://life-experimentalist.github.io/EquiLens/

Code and data accompanying the paper: "Model-Agnostic Bias Measurement in Link Prediction" published in the EACL Findings 2023