Skip to content

Commit

Permalink
updated description and new date
Browse files Browse the repository at this point in the history
  • Loading branch information
@leriomaggio
leriomaggio committed Nov 25, 2024
1 parent 4c30e92 commit 58804c0
Showing 1 changed file with 68 additions and 49 deletions.
117 changes: 68 additions & 49 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,24 +3,32 @@
<head>
<!-- Meta Tags for SEO -->
<meta charset="UTF-8">
<meta name="description" content="Join the Introduction to Privacy-Preserving Machine Learning (PPML) workshop and learn how to protect sensitive data while leveraging the power of machine learning with PySyft and PyTorch.">
<meta name="keywords" content="Privacy-Preserving Machine Learning, PPML, PySyft, PyTorch, OpenMined, Federated Learning, Differential Privacy, Encrypted ML, Workshop">
<meta name="description"
content="Join the Introduction to Privacy-Preserving Machine Learning (PPML) workshop and learn how to protect sensitive data while leveraging the power of machine learning with PySyft and PyTorch.">
<meta name="keywords"
content="Privacy-Preserving Machine Learning, PPML, PySyft, PyTorch, OpenMined, Federated Learning, Differential Privacy, Encrypted ML, Workshop">
<meta name="author" content="Valerio Maggio, OpenMined">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta name="robots" content="index, follow">

<!-- Open Graph Meta Tags for Social Media -->
<meta property="og:title" content="Introduction to Privacy-Preserving Machine Learning Workshop">
<meta property="og:description" content="Learn how to protect sensitive data in machine learning with the Introduction to PPML workshop, using PySyft and PyTorch.">
<meta property="og:image" content="https://openmined.github.io/intro-to-ppml-workshop/assets/imgs/OpenMined-Logo-Stacked-Light.png">
<meta property="og:title"
content="Introduction to Privacy-Preserving Machine Learning Workshop">
<meta property="og:description"
content="Learn how to protect sensitive data in machine learning with the Introduction to PPML workshop, using PySyft and PyTorch.">
<meta property="og:image"
content="https://openmined.github.io/intro-to-ppml-workshop/assets/imgs/OpenMined-Logo-Stacked-Light.png">
<meta property="og:url" content="https://openmined.github.io/intro-to-ppml-workshop/">
<meta property="og:type" content="website">

<!-- Twitter Card Meta Tags -->
<meta name="twitter:card" content="summary_large_image">
<meta name="twitter:title" content="Introduction to Privacy-Preserving Machine Learning Workshop">
<meta name="twitter:description" content="Discover how to protect sensitive data in machine learning with PySyft and PyTorch in this PPML workshop.">
<meta name="twitter:image" content="https://openmined.github.io/intro-to-ppml-workshop/assets/imgs/OpenMined-Logo-Stacked-Light.png">
<meta name="twitter:title"
content="Introduction to Privacy-Preserving Machine Learning Workshop">
<meta name="twitter:description"
content="Discover how to protect sensitive data in machine learning with PySyft and PyTorch in this PPML workshop.">
<meta name="twitter:image"
content="https://openmined.github.io/intro-to-ppml-workshop/assets/imgs/OpenMined-Logo-Stacked-Light.png">

<link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css"
rel="stylesheet"
Expand Down Expand Up @@ -57,7 +65,11 @@
<script async src="https://www.googletagmanager.com/gtag/js?id=G-CGS9YL8FFD"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}

function gtag() {
dataLayer.push(arguments);
}

gtag('js', new Date());

gtag('config', 'G-CGS9YL8FFD');
Expand Down Expand Up @@ -90,17 +102,25 @@ <h1 class="display-3 title">
<div class="col">
<h3><span>Overview</span></h3>
<p>This one-hour live webinar will introduce participants to the fundamentals of
Privacy Preserving Machine Learning (<code>PPML</code>). The session will
introduce key
PPML concepts such as Federated Learning, Differential Privacy, and
Homomorphic Encryption, giving participants a foundational understanding of
how to balance privacy and transparency with the effectiveness of ML models.
During the webinar, attendees will get practical insights into integrating
privacy-preserving techniques into ML workflows using PySyft - an open
source tool for secure and private machine learning.
Privacy Preserving Machine Learning (<code>PPML</code>). 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
<a href="https://docs.openmined.org"
target="_blank"
title="PySyft Documentation">PySyft</a>, a
powerful open-source framework for
secure and private machine learning, alongside <a
href="syftbox-documentation.openmined.org" target="_blank"
title="SyftBox Documentation">SyftBox</a>—OpenMined's latest
project designed to make development with Privacy-Enhancing Technologies
more intuitive and developer-friendly.
</p>
<p>
<a href="https://forms.gle/UvCtBS8kh6mCJSyW8"
<a href="https://forms.gle/n5HHuZCmBah5frHk7"
title="PPML Webinar Registration form" target="_blank">
<span style="font-size: 2.2rem"><strong>Register here</strong></span>
</a>
Expand All @@ -117,20 +137,22 @@ <h3><span>Objectives</span></h3>
<li>Learn the basics of Federated Learning, Differential Privacy, and
Homomorphic Encryption.
</li>
<li>Learn how PySyft enables privacy-preserving Machine learning</li>
<li>Learn how PySyft and SyftBox enables privacy-preserving Machine learning</li>
</ol>
</div>
</div>
</section>
<section id="datetime">
<div class="row">
<div class="col-md-10">
<h3><span> When &amp; When</span></h3>
<h3><span> When &amp; Where</span></h3>
<ul>
<li><strong>Date:</strong> Thursday, 14 November 2024</li>
<li><strong>Time:</strong> 5 PM GMT / 6 PM CET / 12 PM EST / 9 AM PST </li>
<li><strong>Date:</strong> Wednesday, 4 December 2024</li>
<li><strong>Time:</strong> 5 PM GMT / 6 PM CET / 12 PM EST / 9 AM PST</li>
<li><strong>Duration:</strong> 1 hour</li>
<li><strong>Location:</strong> Online (Information will be shared with attendees after registration) </li>
<li><strong>Location:</strong> Online (Information will be shared with
attendees after registration)
</li>
</ul>
</div>
</div>
Expand All @@ -155,29 +177,38 @@ <h3><span>Target Audience</span></h3>
<div class="col-md-10">
<h3><span>Webinar Agenda</span></h3>
<ul class="agenda">
<li><strong>Introduction to PPML and PySyft</strong> (10 minutes):
<li>Opening and Welcome (5 mins)</li>
<li><strong>Introduction to PPML and PETs</strong> (10 minutes):
<ul>
<li>Importance of privacy in Machine learning.</li>
<li>Overview of PySyft as a tool for privacy-preserving ML development.</li>
<li>Intro to PETs: Privacy Enhancing Techniques (PETs)</li>
<li>Different Types of PETs</li>
</ul>
</li>
<li><strong>Core PPML Methods</strong> (30 minutes):
<li><strong>Core PPML Methods</strong> (20 minutes):
<ul>
<li><strong>Federated Learning</strong>: Training models across decentralized data
<li><strong>Federated Learning</strong>: Training models across
decentralized data
sources.
</li>
<li><strong>Differential Privacy</strong>: Adding noise to data to maintain
<li><strong>Differential Privacy</strong>: Adding noise to data to
maintain
individual privacy in ML models.
</li>
<li><strong>Homomorphic Encryption</strong>: Secure computations on encrypted
<li><strong>Homomorphic Encryption</strong>: Secure computations on
encrypted
data.
</li>

</ul>
</li>
<li><strong>PPML in PySyft with Structured Transparency</strong> (10 minutes):
<li><strong>OpenMined and Privacy Tools</strong> (15 minutes):
minutes):
<ul>
<li>PPML in practice using PySyft, and the Structured Transparency framework</li>
<li>PPML in practice using PySyft, and the Structured Transparency
framework
</li>
<li>SyftBox at a first glance!</li>
</ul>
</li>
<li><strong>Q&amp;A Session</strong> (10 minutes):
Expand All @@ -193,29 +224,17 @@ <h3><span>Webinar Agenda</span></h3>
<div class="row">
<div class="col">
<h3><span>Takeaways</span></h3>
<p>Participants will leave with a solid understanding of PPML, its importance, and how it can be
<p>Participants will leave with a solid understanding of PPML, its importance,
and how it can be
applied to machine learning or data science workflows.</p>
<p>This webinar is an ideal starting point for professionals seeking hands-on tools like PySyft to
ensure data privacy while leveraging the full potential of machine learning in sensitive
<p>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.</p>
</div>
</div>
</section>
<section id="materials">
<div class="row">
<div class="col">
<h3><span>Materials</span>
<img src="./assets/imgs/gh-logo.png" class="gh-logo"/></h3>
<p>Materials will be made available on this
<a href="https://github.com/openmined/intro-to-ppml"
title="Intro to PPML Repository" target="_blank">
<strong>Github Repository</strong>
</a>
in due course.
</p>
</div>
</div>
</section>
</div>
</main>
</body>
Expand Down

0 comments on commit 58804c0

Please sign in to comment.