Related papers: Toward Exact Convergence in Byzantine-Robust Decen…
We study stochastic gradient descent (SGD) with local iterations in the presence of malicious/Byzantine clients, motivated by the federated learning. The clients, instead of communicating with the central server in every iteration, maintain…
Federated recommendation systems can provide good performance without collecting users' private data, making them attractive. However, they are susceptible to low-cost poisoning attacks that can degrade their performance. In this paper, we…
We introduce the paradigm of validated decentralized learning for undirected networks with heterogeneous data and possible adversarial infiltration. We require (a) convergence to a global empirical loss minimizer when adversaries are…
Byzantine-robust distributed learning (BRDL), in which computing devices are likely to behave abnormally due to accidental failures or malicious attacks, has recently become a hot research topic. However, even in the independent and…
We study distributed stochastic gradient descent (SGD) in the master-worker architecture under Byzantine attacks. We consider the heterogeneous data model, where different workers may have different local datasets, and we do not make any…
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…
Implementations of SGD on distributed systems create new vulnerabilities, which can be identified and misused by one or more adversarial agents. Recently, it has been shown that well-known Byzantine-resilient gradient aggregation schemes…
This paper proposes a Robust Gradient Classification Framework (RGCF) for Byzantine fault tolerance in distributed stochastic gradient descent. The framework consists of a pattern recognition filter which we train to be able to classify…
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…
Privacy and Byzantine resilience (BR) are two crucial requirements of modern-day distributed machine learning. The two concepts have been extensively studied individually but the question of how to combine them effectively remains…
This paper investigates the problem of decentralized resource allocation in the presence of Byzantine attacks. Such attacks occur when an unknown number of malicious agents send random or carefully crafted messages to their neighbors,…
Distributed learning has become the standard approach for training large-scale machine learning models across private data silos. While distributed learning enhances privacy preservation and training efficiency, it faces critical challenges…
Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either makes use of auxiliary data at parameter server to verify…
In this paper, two reputation based algorithms called Reputation and audit based clustering (RAC) algorithm and Reputation and audit based clustering with auxiliary anchor node (RACA) algorithm are proposed to defend against Byzantine…
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…
Most existing Byzantine-robust federated learning (FL) methods suffer from slow and unstable convergence. Moreover, when handling a substantial proportion of colluded malicious clients, achieving robustness typically entails compromising…
We study the problem of Byzantine fault tolerance in a distributed optimization setting, where there is a group of $N$ agents communicating with a trusted centralized coordinator. Among these agents, there is a subset of $f$ agents that may…
Traditional statistical methods need to be updated to work with modern distributed data storage paradigms. A common approach is the split-and-conquer framework, which involves learning models on local machines and averaging their parameter…
We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a tight statistical rate in terms of all the…
Decentralized learning, which facilitates joint model training across geographically scattered agents, has gained significant attention in the field of signal and information processing in recent years. While the optimization errors of…