Apple Workshop on Privacy-Preserving Machine Learning & AI 2026

Apple hosted the Workshop on Privacy-Preserving Machine Learning & AI earlier this year, emphasizing the importance of privacy-preserving techniques as AI becomes more integrated into daily life.
The workshop focused on three main areas: Private Learning and Statistics, Foundation Models and Privacy, and Attacks and Security.
Discussions covered topics like federated learning, statistical learning, trust models, attacks, privacy accounting, and the challenges posed by foundation models.
Selected presentations were recorded and highlighted include advancements and ongoing challenges in privacy and ML.
Prominent contributors at the workshop included researchers from Apple as well as academia from institutions like the University of Toronto, CISPA, and the University of Massachusetts Amherst.
Notable presentations and discussions also focused on memory memorization in models, differentially private techniques, and the effectiveness of open large language models in private adaptations.