arXiv research

Byrd-SAGA reduces variance to robustify SGD against Byzantine attacks.

Paper tackles Byzantine attacks in Federated Learning by clustering and robustifying.

Paper tackles Byzantine attacks in distributed learning with a new ADMM method.

Paper addresses Byzantine attacks in decentralized optimization over networks.

New attack strategy circumvents CC framework's defences in federated learning.

Novel algorithm resists Byzantine attacks in federated learning for PCA and LRCS.

New methods improve Byzantine robustness in distributed learning.

We propose three new robust aggregation rules for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilie…

New method improves model accuracy in Byzantine-robust distributed learning by optimizing batch size.

We propose a novel robust aggregation rule for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilience…

PRISM-FCP improves federated prediction robustness against Byzantine attacks.

Paper develops a robust federated recommendation system against poisoning attacks.

Paper shows data poisoning and Byzantine attacks are equivalent, impacting federated learning security.

Paper addresses robust federated linear bandits against Byzantine attacks.

Paper develops Byzantine-resilient algorithms for decentralized learning.

This paper extends Newton's method to distributed learning, avoiding saddle points and handling Byzantine workers.

Proposes a method to improve Byzantine-robustness in compressed federated learning.

Two novel algorithms improve distributed machine learning in the presence of Byzantine adversaries.

In this work, we consider the resilience of distributed algorithms based on stochastic gradient descent (SGD) in distributed learning with potentially Byzantine attackers, who could send arbitrary information to the parameter server to disrupt the training process. Toward this end, we propose a new Lipschitz-inspired c…

Novel asynchronous SGD method resists Byzantine attacks without server storage.

Dynamic defense against Byzantine poisoning in federated learning.

Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robu…

In this paper, we show synchronization for a group of output passive agents that communicate with each other according to an underlying communication graph to achieve a common goal. We propose a distributed event-triggered control framework that will guarantee synchronization and considerably decrease the required comm…

New bucketing scheme improves Byzantine robustness for heterogeneous data.

CyBeR-0 optimizes federated learning with Byzantine resilience and reduced communication costs.

This paper considers the problem of detection in distributed networks in the presence of data falsification (Byzantine) attacks. Detection approaches considered in the paper are based on fully distributed consensus algorithms, where all of the nodes exchange information only with their neighbors in the absence of a fus…

New algorithm resists Byzantine attacks in distributed SGD for heterogeneous data.

DynBRO learns robustly from dynamic Byzantine workers.

New algorithm improves decentralized learning in the presence of Byzantine faults.

New framework detects and removes malicious model updates in federated learning.

The recent advances in sensor technologies and smart devices enable the collaborative collection of a sheer volume of data from multiple information sources. As a promising tool to efficiently extract useful information from such big data, machine learning has been pushed to the forefront and seen great success in a wi…

Asynchronous distributed machine learning solutions have proven very effective so far, but always assuming perfectly functioning workers. In practice, some of the workers can however exhibit Byzantine behavior, caused by hardware failures, software bugs, corrupt data, or even malicious attacks. We introduce \emph{Karda…

While machine learning is going through an era of celebrated success, concerns have been raised about the vulnerability of its backbone: stochastic gradient descent (SGD). Recent approaches have been proposed to ensure the robustness of distributed SGD against adversarial (Byzantine) workers sending poisoned gradients …

Unified framework for Byzantine robust gossip algorithms with guaranteed performance.

New research shows Byzantine failures hurt generalization more than data poisoning in robust distributed learning.

We study robust distributed learning that involves minimizing a non-convex loss function with saddle points. We consider the Byzantine setting where some worker machines have abnormal or even arbitrary and adversarial behavior. In this setting, the Byzantine machines may create fake local minima near a saddle point tha…

A method to robustly federate learning with non-i.i.d. data and Byzantine workers.

While the last few decades have witnessed a huge body of work devoted to inference and learning in distributed and decentralized setups, much of this work assumes a non-adversarial setting in which individual nodes---apart from occasional statistical failures---operate as intended within the algorithmic framework. In r…

Proposes a method for private aggregation in heterogeneous federated learning.

Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased local datasets, and poisoning attacks. In this paper we introduce Adaptive Federa…

We consider the problem of distributed statistical machine learning in adversarial settings, where some unknown and time-varying subset of working machines may be compromised and behave arbitrarily to prevent an accurate model from being learned. This setting captures the potential adversarial attacks faced by Federate…

Distributed learning is central for large-scale training of deep-learning models. However, they are exposed to a security threat in which Byzantine participants can interrupt or control the learning process. Previous attack models and their corresponding defenses assume that the rogue participants are (a) omniscient (k…

LiuBei is a resilient ML algorithm that tolerates Byzantine workers and servers without trusting any component.

Machine Learning (ML) solutions are nowadays distributed, according to the so-called server/worker architecture. One server holds the model parameters while several workers train the model. Clearly, such architecture is prone to various types of component failures, which can be all encompassed within the spectrum of a …

Two algorithms improve federated learning efficiency and resilience.

Distributed machine learning algorithms enable learning of models from datasets that are distributed over a network without gathering the data at a centralized location. While efficient distributed algorithms have been developed under the assumption of faultless networks, failures that can render these algorithms nonfu…

SignSGD improves distributed learning by tolerating faulty devices, including Byzantine adversaries.

Paper improves statistical efficiency of median-of-means estimator for Byzantine robust distributed inference.