Name: ManaTEE: Enabling Verifiable AI Transparency With Confidential Computing - Dayeol Lee & Mingshen Sun, TikTok
Start: 2025-08-26T11:55:00+0200
End: 2025-08-26T12:35:00+0200

25-27, August 2025
Amsterdam, Netherlands
View More Details & Registration
Note: The schedule is subject to change.

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for Open Source Summit Europe 2025 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in Central European Summer Time, CEST (UTC +2). To see the schedule in your preferred timezone, please select from the drop-down menu to the right.

IMPORTANT NOTE: Timing of sessions and room locations are subject to change.

Tuesday August 26, 2025 11:55 - 12:35 CEST

TBA

ManaTEE is an open-source framework that enables private data analytics for public research using Trusted Execution Environments (TEEs). In this talk, we show how ManaTEE supports verifiable AI transparency, especially for proprietary models where open inspection is not feasible. TEEs allow sensitive model evaluation and data analysis in isolated, secure environments with cryptographic attestation, ensuring the integrity of both the model and data. This enables external researchers and auditors to assess AI systems without direct access to the model or sensitive data. ManaTEE simplifies this process with a secure, interactive Jupyter Notebook interface where users can load benchmarks, write evaluation code, and analyze results—preserving data confidentiality and model secrecy. We will demo how ManaTEE evaluates a closed-source AI model in a reproducible and auditable way, helping balance the need for transparency with confidentiality.

Speakers

Dayeol Lee

Research Scientist, TikTok

Dayeol Lee is currently a research scientist at TikTok's Privacy Innovation Lab. His research interests are system security, trusted computing, and computer architecture. He earned his Ph.D. in Electrical Engineering and Computer Sciences from the University of California, Berkeley... Read More →

Mingshen Sun

Research Scientist, TikTok

Mingshen is leading application and innovation of the trusted/confidential computing technologies at TikTok. Previously, he worked on multiple open-source projects towards building safe, secure and trustworthy systems. Mingshen also published papers and gave talks on topics at the... Read More →

Tuesday August 26, 2025 11:55 - 12:35 CEST
TBA

Digital Trust

Audience Experience Level Beginner

Open Source Summit Europe 2025

Dayeol Lee

Mingshen Sun

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!