/Awesome-ML-Model-Governance

This repository provides a curated list of references about Machine Learning Model Governance, Ethics, and Responsible AI.

Creative Commons Zero v1.0 UniversalCC0-1.0

Awesome ML Model Governance

Model Governance, Ethics, Responsible AI

  1. Book: "Responsible AI". 2022. by Patrick Hall, Rumman Chowdhury. O'Reilly Media, Inc.
  2. Book: "Practical Fairness". 2020. By Aileen Nielsen. O'Reilly Media, Inc.
  3. Book: "Fairness and machine learning: Limitations and Opportunities." Barocas, S., Hardt, M. and Narayanan, A., 2018.
  4. What are model governance and model operations? A look at the landscape of tools for building and deploying robust, production-ready machine learning models
  5. Specialized tools for machine learning development and model governance are becoming essential. Why companies are turning to specialized machine learning tools like MLflow.
  6. What are model governance and model operations? – O’Reilly
  7. AI Fairness 360, A Step Towards Trusted AI - IBM Research
  8. Responsible AI
  9. Learn how to integrate Responsible AI practices into your ML workflow using TensorFlow
  10. ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT)
  11. Programming Fairness in Algorithms. Understanding and combating issues of fairness in supervised learning.
  12. Secure, privacy-preserving and federated machine learning in medical imaging
  13. Explainable AI (Gartner Prediction for 2023)
  14. What We've Learned to Control. By Ben Recht
  15. Practical Data Ethics
  16. Vasudevan, Sriram and Kenthapadi, Krishnaram. "LiFT: A Scalable Framework for Measuring Fairness in ML Applications" (2020) - Code: The LinkedIn Fairness Toolkit (LiFT)
  17. Four Principles of Explainable Artificial Intelligence (NIST Draft). Phillips, P.J., Hahn, A.C., Fontana, P.C., Broniatowski, D.A. and Przybocki, M.A., 2020.
  18. Data Ethics Canvas. Helps identify and manage ethical issues – at the start of a project that uses data, and throughout. Also see Ethics Canvas for broader scope.
  19. ABOUT ML - Annotation and Benchmarking on Understanding and Transparency of Machine learning Lifecycles.
  20. Mitchell, Margaret and Wu, Simone and Zaldivar, Andrew and Barnes, Parker and Vasserman, Lucy and Hutchinson, Ben and Spitzer, Elena and Raji, Inioluwa Deborah and Gebru, Timnit. "Model Cards for Model Reporting" (2019) - Code: Model Card Toolkit
  21. Navigate the road to Responsible AI – Gradient Flow Blog
  22. 😈 Awful AI is a curated list to track current scary usages of AI - hoping to raise awareness
  23. Seven legal questions for data scientists
  24. 2020 in Review: 8 New AI Regulatory Proposals from Governments
  25. Model Governance resources
  26. ML Cards for D/MLOps Governance (The combination of code, data, model, and service cards for D/MLOps, as an integrated solution.)
  27. To regulate AI, try playing in a sandbox
  28. Biases in AI Systems. A survey for practitioners
  29. Artificial Intelligence Incident Database

Security for ML

  1. Cybersecurity for Data Science
  2. Artifical intelligence and machine learning security (by Microsoft) The references therein are useful.
  3. Evtimov, Ivan, Weidong Cui, Ece Kamar, Emre Kiciman, Tadayoshi Kohno, and Jerry Li. "Security and Machine Learning in the Real World." arXiv (2020).
  4. Machine Learning Systems: Security
  5. Enterprise Security and Governance MLOps (by Diego Oppenheimer)
  6. Adversarial Machine Learning 101
  7. ATLAS - Adversarial Threat Landscape for Artificial-Intelligence Systems

Reports

  1. State of AI Ethics June 2020 Report by the Montreal AI Ethics Institute
  2. State of AI Ethics October 2020 Report by the Montreal AI Ethics Institute
  3. State of AI Ethics January 2021 Report by the Montreal AI Ethics Institute

Organizations

  1. AI Ethics Impact Group: From Principles to Practice