Subject Granular Differential Privacy in Federated Learning
This paper considers subject level privacy in the FL setting, where a subject is an individual whose private information is embodied by several data items either confined within a single federation user or distributed across multiple federation users. We propose two new algorithms that enforce subject level DP at each federation user locally. Our first algorithm, called LocalGroupDP, is a straightforward application of group differential privacy in the popular DP-SGD algorithm. Our second algorithm is based on a novel idea of hierarchical gradient averaging (HiGradAvgDP) for subjects participating in a training mini-batch. We also show that user level Local Differential Privacy (LDP) naturally guarantees subject level DP. We observe the problem of horizontal composition of subject level privacy loss in FL - subject level privacy loss incurred at individual users composes across the federation. We formally prove the subject level DP guarantee for our algorithms, and also show their effect on model utility loss. Our empirical evaluation on FEMNIST and Shakespeare datasets shows that LocalGroupDP delivers the best performance among our algorithms. However, its model utility lags behind that of models trained using a DP-SGD based algorithm that provides a weaker item level privacy guarantee. Privacy loss amplification due to subject sampling fractions and horizontal composition remain key challenges for model utility.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Subject Membership Inference Attacks in Federated Learning
Privacy attacks on Machine Learning (ML) models often focus on inferring the existence of particular data points in the training data. However, what the adversary really wants to know is if a particular individual's (sub…
Federated LearningDifferentially private cross-silo federated learning
Strict privacy is of paramount importance in distributed machine learning. Federated learning, with the main idea of communicating only what is needed for learning, has been recently introduced as a general approach for …
Federated LearningOn Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Steps
Federated learning is a distributed learning setting where the main aim is to train machine learning models without having to share raw data but only what is required for learning. To guarantee training data privacy and …
Federated LearningPrivate Multi-Task Learning: Formulation and Applications to Federated Learning
Many problems in machine learning rely on multi-task learning (MTL), in which the goal is to solve multiple related machine learning tasks simultaneously. MTL is particularly relevant for privacy-sensitive applications i…
BIG-bench Machine LearningDistributed OptimizationFederated LearningMulti-Task Learning+1Differentially Private Federated Learning: A Systematic Review
In recent years, privacy and security concerns in machine learning have promoted trusted federated learning to the forefront of research. Differential privacy has emerged as the de facto standard for privacy protection i…
Federated LearningPrivacy Preserving