Robust Aggregation for Federated Learning

12/31/2019
by   Krishna Pillutla, et al.
22

We present a robust aggregation approach to make federated learning robust to settings when a fraction of the devices may be sending corrupted updates to the server. The proposed approach relies on a robust secure aggregation oracle based on the geometric median, which returns a robust aggregate using a constant number of calls to a regular non-robust secure average oracle. The robust aggregation oracle is privacy-preserving, similar to the secure average oracle it builds upon. We provide experimental results of the proposed approach with linear models and deep networks for two tasks in computer vision and natural language processing. The robust aggregation approach is agnostic to the level of corruption; it outperforms the classical aggregation approach in terms of robustness when the level of corruption is high, while being competitive in the regime of low corruption.

READ FULL TEXT

page 33

page 38

research
12/23/2021

Sparsified Secure Aggregation for Privacy-Preserving Federated Learning

Secure aggregation is a popular protocol in privacy-preserving federated...
research
02/25/2020

Device Heterogeneity in Federated Learning: A Superquantile Approach

We propose a federated learning framework to handle heterogeneous client...
research
10/06/2021

Secure Byzantine-Robust Distributed Learning via Clustering

Federated learning systems that jointly preserve Byzantine robustness an...
research
04/03/2022

Byzantine-Robust Federated Linear Bandits

In this paper, we study a linear bandit optimization problem in a federa...
research
04/01/2022

Robust and Efficient Aggregation for Distributed Learning

Distributed learning paradigms, such as federated and decentralized lear...
research
09/30/2020

Secure Aggregation with Heterogeneous Quantization in Federated Learning

Secure model aggregation across many users is a key component of federat...
research
01/15/2021

Probabilistic Inference for Learning from Untrusted Sources

Federated learning brings potential benefits of faster learning, better ...

Please sign up or login with your details

Forgot password? Click here to reset