Popular GitHub Repositories for Accountability

A library that implements fairness-aware machine learning algorithms

TraceFL is a novel mechanism for Federated Learning that achieves interpretability by tracking neuron provenance. It identifies clients responsible for global model predictions, achieving 99% accuracy across diverse datasets (e.g., medical imaging) and neural networks (e.g., GPT).

Concise summaries of key papers in responsible AI.

An Ethical AI framework, laying the foundation for success in AI development

关于构建符合伦理、公平、负责任的 AI 系统的文章——即与人类价值观相符的 AI 系统。