The problem of Byzantine resilience in distributed machine learning, aka Byzantine machine
learning, consists of designing distributed algorithms that can train an accurate model …

Byzantine machine learning (ML) aims to ensure the resilience of distributed learning
algorithms to misbehaving (or Byzantine) machines. Although this problem received …

In Byzantine robust distributed or federated learning, a central server wants to train a
machine learning model over data distributed across multiple workers. However, a fraction …

The theory underlying robust distributed learning algorithms, designed to resist adversarial
machines, matches empirical observations when data is homogeneous. Under data …

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine
attackers can send arbitrary gradients to a central server to destroy the convergence and …

To study the resilience of distributed learning, the “Byzantine" literature considers a strong
threat model where workers can report arbitrary gradients to the parameter server. Whereas …

Federated learning (FL) is susceptible to Byzantine attacks due to its inherently distributed
and privacy-preserving nature. Most model parameters-based defense methods become …

The geometric median, an instrumental component of the secure machine learning toolbox,
is known to be effective when robustly aggregating models (or gradients), gathered from …

Abstract Propose-Test-Release (PTR) is a differential privacy framework that works with
local sensitivity of functions, instead of their global sensitivity. This framework is typically …

This work studies the problem of reliably estimating a subspace in a federated setting, when
some nodes' outputs can be compromised by Byzantine attacks. Typically, the subspace of …