Apple has published four recordings and research summaries from its 2026 Workshop on Privacy-Preserving Machine Learning and AI. Here are the details:
Apple releases video about ML and privacy workshop
Apple has published a new post on its Machine Learning blog containing four featured talks from the 2026 Workshop on Privacy Preserving Machine Learning and AI.
During this two-day event, Apple researchers and members of the broader research community discussed “The latest advances in privacy-preserving ML and AI,” with a focus on private learning and statistics, underlying models and privacy, and attacks and security.
Here’s what Apple has to say about the event:
Workshop presentations and discussions explored advances and open questions in privacy and ML, including federated learning, statistical learning, trust models, attacks, privacy accounting, and the unique challenges posed by underlying models. These research areas build on innovations in rigorous privacy and security assessments and bridge theoretical frameworks with real-world applications.
In a blog post, Apple featured four talks, including a “Crypto for DP and DP for Crypto” presentation by Kunal Talwar, a research scientist at the company.
You can watch it below.
Additionally, other notable talks include:
- Online Matrix Factorization and Online Query Release (presented by Alexander Nikolov, University of Toronto)
- “Learning from the People: Communicating S&P Technologies for Responsible Data Collection,” a talk by Elissa Redmiles, Georgetown.
- Understanding and Reducing Memory in Basic Models – Presented by Franziska Boenisch from CISPA
Apple also highlighted 24 published works presented at the workshop, including three papers developed by the company’s current and former researchers.
Click this link to watch all sessions and see a complete list of referenced papers.
Worth checking out on Amazon
FTC: We use automated affiliate links that generate income. more.
