09-25, 14:40–15:15 (Europe/Amsterdam), Voyager
Privacy-Enhancing Technologies (PETs) promise to bridge the gap between data utility and privacy — but how do they perform in practice? In this talk, we’ll share real-world insights from our hands-on experience testing and implementing leading PET solutions across various data science use cases.
We explored tools such as differential privacy libraries, homomorphic encryption frameworks, federated learning, multi-party computation, etc. Some lived up to their promise — others revealed critical limitations.
You’ll walk away with a clear understanding of which PET solutions work best for which types of data and analysis, what trade-offs to expect, and how to set realistic goals when integrating PETs into your workflows. This session is ideal for data professionals and decision-makers who are navigating privacy risks while still wanting to innovate responsibly.
In a world where data-driven innovation often clashes with growing privacy demands, Privacy-Enhancing Technologies (PETs) are gaining momentum. But theory and whitepapers are one thing — practical implementation is another. In this 30-minute talk, we take you behind the scenes of real-life data science projects where PETs were tested and applied.
You'll hear honest, experience-based insights about what worked, what didn’t, and why. We’ll cover widely known approaches like differential privacy, homomorphic encryption, federated learning, multi-party computation— and show where each one fits (or doesn’t) in real-world settings.
Whether you’re working in healthcare, government, HR, or finance, you’ll learn:
• How to match PET tools with specific use cases
• Where the trade-offs lie in utility, scalability, and compliance
• What technical and organizational conditions are needed for success
This session is fast-paced, practical, and designed for anyone balancing innovation with responsible data use — from data scientists and engineers to compliance leads and product managers.