arXiv research

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

COMRADE is a communication-efficient, Byzantine-resilient second-order optimization algorithm.

Paper develops Byzantine-resilient algorithms for decentralized learning.

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

Efficient distributed learning with Byzantine-resilient thresholding and error feedback.

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

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

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

Paper develops efficient algorithms for robust distributed learning with statistical guarantees.

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 …

Byzantine-resilient federated learning with local iterations and robust mean estimation.

PRISM-FCP improves federated prediction robustness against Byzantine attacks.

The paper addresses private and Byzantine-proof cooperative decision-making in multi-agent systems.

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…

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

Unified framework for Byzantine robust gossip algorithms with guaranteed performance.

We propose Zeno++, a new robust asynchronous Stochastic Gradient Descent~(SGD) procedure which tolerates Byzantine failures of the workers. In contrast to previous work, Zeno++ removes some unrealistic restrictions on worker-server communications, allowing for fully asynchronous updates from anonymous workers, arbitrar…

Paper addresses robust federated linear bandits against Byzantine attacks.

Paper proposes a secure protocol for federated learning.

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

Study cooperative bandit learning with imperfect communication, achieving near-optimal performance.

Proposes a method for private aggregation in heterogeneous federated learning.

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

New algorithm identifies near-optimal policies in adversarial distributed RL settings.

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

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithm…

Two algorithms improve federated learning efficiency and resilience.

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

Paper addresses Byzantine attacks in decentralized optimization over networks.

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

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

Novel asynchronous SGD method resists Byzantine attacks without server storage.

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…

DynBRO learns robustly from dynamic Byzantine workers.

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…

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…

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…

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…

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…

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

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

New methods improve Byzantine robustness in distributed learning.

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

The growth of data, the need for scalability and the complexity of models used in modern machine learning calls for distributed implementations. Yet, as of today, distributed machine learning frameworks have largely ignored the possibility of arbitrary (i.e., Byzantine) failures. In this paper, we study the robustness …

Robust algorithm for distributed optimization resistant to Byzantine failures.

Paper develops a robust federated recommendation system against poisoning attacks.

Machine learning has begun to play a central role in many applications. A multitude of these applications typically also involve datasets that are distributed across multiple computing devices/machines due to either design constraints (e.g., multiagent systems) or computational/privacy reasons (e.g., learning on smartp…

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