Course Abstract

Training duration : 90 minutes

AI, especially machine learning based on neural nets, is seen as a key technology in the digitization of society and its private and public sectors. But the normal workflow of such AI is normally at odds with data privacy, which is becoming more and more important to consumers and regulators alike. This poses a challenge for the acceptability and wider adoption or AI, including its use in edge environments. Federated learning is seen as an approach for collaborative and distributed AI that has the potential to resolve this challenge while also creating AI models with high utility. This session will introduce its concept and discuss one of its instances, the open-source framework XayNet, in greater detail, first in a hands-off and then in a hands-on manner through a demo of XayNet.

DIFFICULTY LEVEL: ADVANCED

Learning Objectives

  • Understanding what the privacism movement is and why it matters for DS/AI/ML

  • Comprehending that today’s practice of AI is at odds with that movement and, increasingly, with territorial regulation of data processing and data movement

  • Understanding the concept of federated learning and acknowledging that is has potential to support tomorrow’s regulated AI as well as the privacism movement

  • Gaining familiarity with the technical aspects of federated learning for its standard algorithm, federated averaging

  • Achieving familiarity with a privacy-preserving version of federated learning, the open-source framework https://github.com/XayNetwork/XayNet

  • Understanding why/how the XayNet framework preserves privacy as well as the utility of vertical or horizontal AI use cases

  • Becoming familiar with the usage of the XayNet framework for a “hello world” AI use case in a tutorial demo session, including installation, configuration, and execution.

Instructor

Instructor Bio:

"Professor Michael Huth (Ph.D.) is Co-Founder and CTO of the technology company XAIN and teaches at Imperial College London. His research focuses on Cybersecurity, Cryptography, Mathematical Modeling, as well as security and privacy in Machine Learning. He served as the technical lead of the Harnessing Economic Value theme at PETRAS IoT Cybersecurity Research Hub in the UK. In 2017, he founded XAIN AG together with Leif-Nissen Lundbæk and Felix Hahmann. The Berlin-based company aims to solve the challenge of combining AI with privacy with an emphasis on Federated Learning. XAIN won the first Porsche Innovation Contest and has already worked successfully with Porsche AG, Daimler AG, Deutsche Bahn, and Siemens. Professor Huth studied Mathematics at TU Darmstadt and obtained his Ph.D. at Tulane University, New Orleans. He worked at TU Darmstadt, Kansas State University and spent a research sabbatical at The University of Oxford. Huth has authored several scientific publications and is an experienced speaker on international stages."

Michael Huth, PhD

Co-Founder and CTO | XAIN AG

Course Outline

Module 1: What is federated learning and why does it matter? 

-Strategic context (e.g. AI on the edge and upcoming regulation of AI), technical background (e.g. the federated averaging algorithm), and legal background (e.g. basic principles of data privacy common to EU GDPR and CCPA). 

- Discussion of the familiar trade-off between privacy and utility in AI use cases, and show that federated learning can resolve this dilemma (e.g. with experimental evidence on a standard voice recognition benchmark)

 - Develop an approach to federated learning that not only resolves the above dilemma but also complies with regulation around data privacy: the open-source framework XayNet.

 -XayNet discussion focusing on how its protocol for federated learning preserves privacy (in the legal sense) without compromising the ability for scalable performance. 

Module 2: How to use the open-source XayNet for federated learning.

- Hands-on demo to use the framework, how it can be configured for a “hello world” AI use case 

- What UI support there is for running and monitoring the execution of this federated learning use case

Background knowledge

  • This course is for current and aspiring Data Scientists, Machine Learning Engineers, AI Product Managers

  • Knowledge of following tools and concepts is useful:

  • Learners should have some familiarity with machine learning and its algorithms but neither prior knowledge about federated learning nor of its potential value and technical issues

  • Some familiarity with programming languages

  • The replication of the demo in this course will require a stable tool chain for the programming language Rust, and standard tools for installation and editing to build own use-case.

Real-world applications

  • Insurance and banking industries are actively deploying federated learning frameworks for risk control management.

  • Federated learning has the potential to allow ML models in healthcare to reach its full potential to access medical data while preserving privacy.

  • Federated learning helps put the focus on dealing with customer privacy and regulatory compliance in various enterprise use-cases