Introduction to Privacy Preserving Machine Learning

Overview

This one-hour live webinar will introduce participants to the fundamentals of Privacy Preserving Machine Learning (PPML). The session explores essential PPML concepts including Federated Learning, Differential Privacy, and Homomorphic Encryption, providing participants with a foundational understanding of balancing privacy and transparency in ML model development. Through practical demonstrations, attendees will learn to integrate privacy-preserving techniques into ML workflows using OpenMined. Participants will explore PySyft, a powerful open-source framework for secure and private machine learning, alongside SyftBox—OpenMined's latest project designed to make development with Privacy-Enhancing Technologies more intuitive and developer-friendly.

Register here

Objectives

  1. Understand the core concepts and the importance of PPML.
  2. Learn the basics of Federated Learning, Differential Privacy, and Homomorphic Encryption.
  3. Learn how PySyft and SyftBox enables privacy-preserving Machine learning

When & Where

  • Virtual Sessions: Wed. 4 December 2024, and Wed. 18 December 2024
  • Time: 5 PM GMT / 6 PM CET / 12 PM EST / 9 AM PST
  • Duration: 1 hour
  • Location: Online (Information will be shared with attendees after registration)

Target Audience

This webinar is designed for data scientists, AI practitioners, machine learning engineers, and developers interested in applying privacy-preserving techniques to their ML models, especially those working with sensitive data in domains like healthcare, finance, and government.

Webinar Agenda

  • Opening and Welcome (5 mins)
  • Introduction to PPML and PETs (10 minutes):
    • Importance of privacy in Machine learning.
    • Intro to PETs: Privacy Enhancing Techniques (PETs)
    • Different Types of PETs
  • Core PPML Methods (20 minutes):
    • Federated Learning: Training models across decentralized data sources.
    • Differential Privacy: Adding noise to data to maintain individual privacy in ML models.
    • Homomorphic Encryption: Secure computations on encrypted data.
  • OpenMined and Privacy Tools (15 minutes): minutes):
    • PPML in practice using PySyft, and the Structured Transparency framework
    • SyftBox at a first glance!
  • Q&A Session (10 minutes):
    • Addressing participant questions and insights.

Takeaways

Participants will leave with a solid understanding of PPML, its importance, and how it can be applied to machine learning or data science workflows.

This webinar is an ideal starting point for professionals seeking hands-on tools like PySyft and SyftBox to ensure data privacy while leveraging the full potential of machine learning in sensitive environments.