Shift your Thinking: A Practical View of Privacy in AI/ML

Hosted by Katharine Jarmul

Wed, Mar 4, 2026

4:00 PM UTC (30 minutes)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Practical AI Privacy
Katharine Jarmul
View syllabus

What you'll learn

Identifying common privacy mistakes

Classic approaches to privacy or simple fixes don't address the way we build AI systems

Assessing real risks

Rather than looking at all risk in all ways, focus on what risks affect your architecture, system and model choices.

Focusing on what's possible

Adjust your efforts to address where you can make impact. Where can you engineer privacy into the workflow?

Why this topic matters

Too often privacy efforts fail because they focus on the wrong parts of the AI/ML lifecycle. In this lighting lesson, you'll cut through risks that you can't address and focus on measurable impact for real-world AI/ML workflows. By making privacy engineering actionable, you'll walk away with a clearer roadmap to addressing privacy issues in your setup and building safer system

You'll learn from

Katharine Jarmul

Privacy in Machine Learning Systems, Author of Practical Data Privacy

Katharine Jarmul focuses her work and research on privacy and security in data science, deep learning and AI. She is author of the well received O'Reilly book Practical Data Privacy (O'Reilly 2023) and has more than 10 years experience in machine learning/AI where she has helped build large scale AI systems with privacy and security built in. You can follow her work via her newsletter, Probably Private or on her website.

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.