Related papers: LIFT: Byzantine Resilient Hub-Sampling

To defend against Byzantine attacks in decentralized learning, most existing methods rely on robust aggregation rules to mitigate the influence of malicious machines. However, these strategies inherently introduce bias, leading to inexact…

This paper deals with distributed finite-sum optimization for learning over networks in the presence of malicious Byzantine attacks. To cope with such attacks, most resilient approaches so far combine stochastic gradient descent (SGD) with…

In this paper, we consider the Byzantine-robust stochastic optimization problem defined over decentralized static and time-varying networks, where the agents collaboratively minimize the summation of expectations of stochastic local cost…

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…

Replication protocols are essential for distributed systems, ensuring consistency, reliability, and fault tolerance. Traditional Crash Fault Tolerant (CFT) protocols, which assume a fail-stop model, are inadequate for untrusted cloud…

Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers. Recent GL approaches rely on dynamic communication graphs built and maintained using…

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…

Federated learning (FL) enables multiple participants to train a global machine learning model without sharing their private training data. Peer-to-peer (P2P) FL advances existing centralized FL paradigms by eliminating the server that…

The ability to perform repeated Byzantine agreement lies at the heart of important applications such as blockchain price oracles or replicated state machines. Any such protocol requires the following properties: (1) \textit{Byzantine…

Sybil attacks, in which a large number of adversary-controlled nodes join a network, are a concern for many peer-to-peer database systems, necessitating expensive countermeasures such as proof-of-work. However, there is a category of…

Approximate byzantine consensus is a fundamental problem of distributed computing. This paper presents a novel algorithm for approximate byzantine consensus, called Relay-ABC. The algorithm allows machines to achieve approximate consensus…

Byzantine fault-tolerant agreement (BFT) in a partially synchronous system usually requires 3f + 1 nodes to tolerate f faulty replicas. Due to their high throughput and finality property BFT algorithms build the core of recent permissioned…

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…

We address the challenges of Byzantine-robust training in asynchronous distributed machine learning systems, aiming to enhance efficiency amid massive parallelization and heterogeneous computing resources. Asynchronous systems, marked by…

Multi-task learning is an effective way to address the challenge of model personalization caused by high data heterogeneity in federated learning. However, extending multi-task learning to the online decentralized federated learning setting…

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…

Traditional Byzantine Fault Tolerance (BFT) state machine replication protocols assume a partial synchrony model, leading to a design where a leader replica drives the protocol and is replaced after a timeout. Recently, we witnessed a surge…

Service replication distributes an application over many processes for tolerating faults, attacks, and misbehavior among a subset of the processes. The established state-machine replication paradigm inherently requires the application to be…

In this paper, we propose BR-MTRL, a Byzantine-resilient multi-task representation learning framework that handles faulty or malicious agents. Our approach leverages representation learning through a shared neural network model, where all…

We study adversary-resilient stochastic distributed optimization, in which $m$ machines can independently compute stochastic gradients, and cooperate to jointly optimize over their local objective functions. However, an $\alpha$-fraction of…