Apple has released four recordings and a summary of research from its 2026 Workshop on Privacy-Preserving Machine Learning and Artificial Intelligence. Here are the details.
Apple publishes videos on ML and privacy workshop
Apple has published a new post on their machine learning blog with four featured talks from their 2026 Workshop on Privacy-Preserving Machine Learning and Artificial Intelligence.
In this two-day event, Apple researchers and members of the broader research community discussed “the latest in privacy-preserving machine learning and artificial intelligence,” focusing on private learning and statistics, basic 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 basic models. These research areas base innovation on rigorous assessment of privacy and security, bridging 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 see it below:
Additionally, other notable talks include:
- Online matrix factorization and online query publishing, presented by Aleksandar Nikolov from the University of Toronto
- Learning from People: Communicating about S&P’s technology for responsible data collection, presented by Georgetown’s Elissa Redmiles
- Understanding and mitigating rote memorization in basic models: presented by Franziska Boenisch of CISPA
Apple also highlighted 24 published papers presented at the workshop, including three papers developed by current and former researchers at the company:
To view all sessions and see the full list of referenced articles, follow this link.
Worth checking out on Amazon
FTC: We use automatic affiliate links that generate income. Further.
