🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

A collection of awesome software, libraries, learning tutorials, documents, books & technical resources and cool stuff about dark web.

A collection of resources and tools designed to provide guidelines for ethical modeling.

Credo AI Lens is a comprehensive assessment framework for AI systems. Lens standardizes model and data assessment, and acts as a central gateway to assessments created in the open source community.

Alpha principles for the ethical use of AI and Data Driven Technologies in Ontario | Proposition de principes pour une utilisation éthique des technologies axées sur les données en Ontario

Fair Statistical Learning Algorithms for Ethical Artificial Intelligence

Package for evaluating the performance of methods which aim to increase fairness, accountability and/or transparency

This is the OFFICIAL CybernetiX S3C website.

Source code and models for the paper "Cyberbullying Detection with Fairness Constraints". IEEE Internet Computing, 2020

Master thesis: Exploring bias in German NLG (GPT-3 & GerPT-2). Applies regard classification and bias mitigation triggers.

Evaluation & testing framework for computer vision models

Minimize the risks and maximize the benefits of using data-driven technologies within government processes, programs and services through transparency. | Réduire les risques et à maximiser les avantages liés à l’utilisation de technologies axées sur les données, dans le cadre de processus, programmes et services gouvernementaux, grâce à la trans…

[AAAI 2018] Implementation of the Ethics Shaping approach proposed in "A low-cost ethics shaping approach for designing reinforcement learning agents"

Build confidence in your AI with systematic slice-based testing

Etica.AI is concerned about long-term social & ethical implications of artificial intelligence on Africa/Latin America. Do it via grassroots acts in short-term

Debiasing word embeddings

This repository has details regarding books read and to be read by the AICN Ethics Bookclub

The Open Ethics Canvas is a tool for developers, product owners, and ethics professionals. It could be used as a conversation starter in the process of building transparent and explainable technology products.

Paper list and relevant material for Privacy-Preserving Computation.

This project involves analyzing TikTok videos to classify claims vs. opinions using Python. It includes EDA, statistical tests, logistic regression, and ML models (Random Forest, XGBoost) to support content moderation. Built with pandas, scikit-learn, and Tableau, the solution helps TikTok automate content review and enhance moderation efficiency.