Apple shares recordings and research from recent privacy-focused AI and ML workshop

Apple has released four recordings and a research summary from its 2026 workshop on privacy-preserving machine learning and AI. Here are the details.

Apple releases ML videos and privacy workshop

Apple has published a new post on its machine learning blog with four featured talks from its 2026 workshop on machine learning and privacy-preserving AI.

During the two-day event, Apple researchers and members of the broader research community discussed the “latest in privacy-preserving ML and AI,” focusing on private learning and statistics, core models and privacy, and attacks and security.

Here’s Apple at the event:

Presentations and discussions at the workshop explored advances and open questions in privacy and ML, including federated learning, statistical learning, trust models, attacks, privacy accounting, and the unique challenges presented by foundation models. These research areas ground innovation in rigorous assessment of privacy and security, connecting theoretical frameworks with real-world applications.

In its blog post, Apple featured four talks, including the “Crypto for DP and DP for Crypto” presentation, given by the company’s research scientist Kunal Talwar.

You can watch it below:

Additionally, other featured conferences include:

Online matrix factorization and online query publishing, presented by Aleksandar Nikolov of the University of Toronto
Learning from People: Communicating S&P Technology for Responsible Data Collection, presented by Elissa Redmiles of Georgetown
Understanding and mitigating memorization in foundation models – presented by Franziska Boenisch of CISPA

Apple also highlighted 24 published works presented at the workshop, including three papers developed by current and former researchers at the company:

To watch all sessions and see the full list of referenced articles, follow this link.