In our second post we described attacks on models and the concepts of input privacy and output privacy. ln our last post, we described horizontal and vertical partitioning of data in privacy-preserving federated learning (PPFL) systems. In this post, we explore the problem of providing input privacy in PPFL systems for the horizontally-partitioned setting. Models, training, and aggregation To explore techniques for input privacy in PPFL, we first have to be more precise about the training process. In horizontally-partitioned federated learning, a common approach is to ask each participant to

This post is part of a series on privacy-preserving federated learning. The series is a collaboration between NIST and the UK government’s Centre for Data Ethics and Innovation. Learn more and read all the posts published to date at NIST’s Privacy Engineering Collaboration Space or the CDEI blog . Our first post in the series introduced the concept of federated learning—an approach for training AI models on distributed data by sharing model updates instead of training data. At first glance, federated learning seems to be a perfect fit for privacy since it completely avoids sharing data

This post is the first in a series on privacy-preserving federated learning. The series is a collaboration between CDEI and NIST. Advances in machine learning and AI, fueled by large-scale data availability and high-performance computing, have had a significant impact across the world in the past two decades. Machine learning techniques shape what information we see online, influence critical business decisions, and aid scientific discovery, which is driving advances in healthcare, climate modelling, and more. Training Models: Conventional vs Federated Learning The standard way to train