Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning

06/07/2021
by   Jinhyun So, et al.
0

Secure aggregation is a critical component in federated learning, which enables the server to learn the aggregate model of the users without observing their local models. Conventionally, secure aggregation algorithms focus only on ensuring the privacy of individual users in a single training round. We contend that such designs can lead to significant privacy leakages over multiple training rounds, due to partial user selection/participation at each round of federated learning. In fact, we empirically show that the conventional random user selection strategies for federated learning lead to leaking users' individual models within number of rounds linear in the number of users. To address this challenge, we introduce a secure aggregation framework with multi-round privacy guarantees. In particular, we introduce a new metric to quantify the privacy guarantees of federated learning over multiple training rounds, and develop a structured user selection strategy that guarantees the long-term privacy of each user (over any number of training rounds). Our framework also carefully accounts for the fairness and the average number of participating users at each round. We perform several experiments on MNIST and CIFAR-10 datasets in the IID and the non-IID settings to demonstrate the performance improvement over the baseline algorithms, both in terms of privacy protection and test accuracy.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/11/2020

Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

Federated learning is gaining significant interests as it enables model ...
02/04/2021

SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregation

For model privacy, local model parameters in federated learning shall be...
10/05/2021

Secure Aggregation for Buffered Asynchronous Federated Learning

Federated learning (FL) typically relies on synchronous training, which ...
07/21/2020

Byzantine-Resilient Secure Federated Learning

Secure federated learning is a privacy-preserving framework to improve m...
04/21/2020

Federated Learning with Only Positive Labels

We consider learning a multi-class classification model in the federated...
03/23/2022

Contextual Model Aggregation for Fast and Robust Federated Learning in Edge Computing

Federated learning is a prime candidate for distributed machine learning...
11/30/2019

Federated Learning with Autotuned Communication-Efficient Secure Aggregation

Federated Learning enables mobile devices to collaboratively learn a sha...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.