Sharing Some Privacy Engineering Resources

Federated Learning

• Federated Learning and Privacy: https://cacm.acm.org/magazines/2022/4/259417-federated-learning-and-privacy/fulltext
• Flower’s federated learning framework: https://flower.dev/
• Medium post:
  • Federated Learning 101 with FEDn – https://medium.com/odscjournal/federated-learning-101-with-fedn-eb8b2c949056
  • Practical Federated Learning with Azure Machine Learning: https://towardsdatascience.com/practical-federated-learning-with-azure-machine-learning-8807f9bd1a7e
• AWS post: Applying Federated Learning for ML at the Edge – https://aws.amazon.com/blogs/architecture/applying-federated-learning-for-ml-at-the-edge/

Synthetic Data

• What Privacy Officers Need to Know About Synthetic Data: https://wirewheel.io/blog/privacy-synthetic-data/
• a potential vendor service: https://mostly.ai/

Differential Privacy

• Code libraries, workshops, papers, website resources: https://differentialprivacy.org/resources/
• Google’s differential privacy open-source library: https://github.com/google/differential-privacy/
• Tutorial: Differential Privacy I: Introduction: https://www.borealisai.com/research-blogs/tutorial-12-differential-privacy-i-introduction/
• Paper “DIFFERENTIAL  PRIVACY  IN  PRACTICE:  EXPOSE  YOUR  EPSILONS!”: https://journalprivacyconfidentiality.org/index.php/jpc/article/view/689/685
• Paper “Calibrating Noise to Sensitivity in Private Data Analysis” (the paper that first time introduced this concept): https://link.springer.com/content/pdf/10.1007/11681878_14.pdf

Homomorphic Encryption

• FastCompany report “Homomorphic encryption could revolutionize privacy – so what is it”: https://www.fastcompany.com/90782408/what-is-homomorphic-encryption-and-why-is-it-a-privacy-holy-grail
• A rebuttal article: https://www.keyfactor.com/blog/what-is-homomorphic-encryption/
• A few introductory posts:
  • https://brilliant.org/wiki/homomorphic-encryption/
  • https://queue.acm.org/detail.cfm?id=3561800
• Microsoft’s HE project: https://www.microsoft.com/en-us/ai/ai-lab-he

(Secure) Multi-party Computation 

• Forbes article (providing some additional sources) Multi-Party Computation: Private Inputs, Public Outputs: https://www.forbes.com/sites/forbestechcouncil/2021/10/26/multi-party-computation-private-inputs-public-outputs/?sh=3dd770b21bb0
• 101: https://www.fireblocks.com/what-is-mpc/
• An online book: A Pragmatic Introduction to
  Secure Multi-Party Computation – https://securecomputation.org/