Related papers: FORTA: Byzantine-Resilient FL Aggregation via DFT-…

Byzantine fault-tolerant (BFT) web services provide critical integrity guarantees for distributed applications but face significant latency challenges that hinder interactive user experiences. We propose a novel two-layer architecture that…

Decentralized federated learning (DFL) enables collaborative model training without centralized trust, but it remains vulnerable to Byzantine clients that poison gradients under heterogeneous (Non-IID) data. Existing defenses face a…

Distributed learning has many computational benefits but is vulnerable to attacks from a subset of devices transmitting incorrect information. This paper investigates Byzantine-resilient algorithms in a decentralized setting, where devices…

Prior efforts in enhancing federated learning (FL) security fall into two categories. At one end of the spectrum, some work uses secure aggregation techniques to hide the individual client's updates and only reveal the aggregated global…

Byzantine Fault Tolerant (BFT) consensus protocols for dynamically available systems face a critical challenge: balancing latency and security in fluctuating node participation. Existing solutions often require multiple rounds of voting per…

Federated learning (FL) is a distributed learning paradigm that preserves users' data privacy while leveraging the entire dataset of all participants. In FL, multiple models are trained independently on the clients and aggregated centrally…

Federated Learning (FL) is notorious for its vulnerability to Byzantine attacks. Most current Byzantine defenses share a common inductive bias: among all the gradients, the densely distributed ones are more likely to be honest. However,…

Byzantine fault tolerant (BFT) state machine replication (SMR) is an important building block for constructing permissioned blockchain systems. In contrast to Nakamoto Consensus where any block obtains higher assurance as buried deeper in…

Federated learning (FL) enables training of a global model while keeping raw data on end-devices. Despite this, FL has shown to leak private user information and thus in practice, it is often coupled with methods such as differential…

Aggregation rules are the cornerstone of distributed (or federated) learning in the presence of adversaries, under the so-called Byzantine threat model. They are also interesting mathematical objects from the point of view of robust mean…

Decentralized learning has gained great popularity to improve learning efficiency and preserve data privacy. Each computing node makes equal contribution to collaboratively learn a Deep Learning model. The elimination of centralized…

This paper explores the territory that lies between best-effort Byzantine-Fault-Tolerant Conflict-free Replicated Data Types (BFT CRDTs) and totally ordered distributed ledgers, such as those implemented by Blockchains. It formally…

This work presents a new distributed Byzantine tolerant federated learning algorithm, HoldOut SGD, for Stochastic Gradient Descent (SGD) optimization. HoldOut SGD uses the well known machine learning technique of holdout estimation, in a…

Arma is a Byzantine Fault Tolerant (BFT) consensus system designed to achieve linear scalability across all hardware resources: network bandwidth, CPU, and disk I/O. As opposed to preceding BFT protocols, Arma separates the dissemination…

Motivated by the ever-increasing concerns on personal data privacy and the rapidly growing data volume at local clients, federated learning (FL) has emerged as a new machine learning setting. An FL system is comprised of a central parameter…

The performance of clients in Federated Learning (FL) can vary due to various reasons. Assessing the contributions of each client is crucial for client selection and compensation. It is challenging because clients often have non-independent…

Federated learning enables a global machine learning model to be trained collaboratively by distributed, mutually non-trusting learning agents who desire to maintain the privacy of their training data and their hardware. A global model is…

We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious…

Byzantine fault-tolerant (BFT) protocols allow a group of replicas to come to a consensus even when some of the replicas are Byzantine faulty. There exist multiple BFT protocols to securely tolerate an optimal number of faults $t$ under…

Motivated by the increasing demand for data security in decentralized federated learning (FL) and stochastic optimization, we formulate and investigate the problem of information-theoretic \emph{decentralized secure aggregation} (DSA).…