Related papers: Byzantine-Tolerant Machine Learning
Secure federated learning enables collaborative model training across decentralized users while preserving data privacy. A key component is secure aggregation, which keeps individual updates hidden from both the server and users, while also…
Adversarial attacks pose a major challenge to distributed learning systems, prompting the development of numerous robust learning methods. However, most existing approaches suffer from the curse of dimensionality, i.e. the error increases…
Byzantine-robustness has been gaining a lot of attention due to the growth of the interest in collaborative and federated learning. However, many fruitful directions, such as the usage of variance reduction for achieving robustness and…
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…
This paper studies the distributed multi-agent resilient optimization problem under the f-total Byzantine attacks. Compared with the previous work on Byzantineresilient multi-agent exact optimization problems, we do not require the…
Consensus, abstracting a myriad of problems in which processes have to agree on a single value, is one of the most celebrated problems of fault-tolerant distributed computing. Consensus applications include fundamental services for the…
We study a recently proposed large-scale distributed learning paradigm, namely Federated Learning, where the worker machines are end users' own devices. Statistical and computational challenges arise in Federated Learning particularly in…
We revisit Byzantine robust distributed estimation for high-dimensional sparse linear models. By combining local $\ell_1$-regularized robust estimation with robust aggregation at the server, the framework applies to pseudo-Huber regression,…
At PODC 2014, A. Most\'efaoui, H. Moumen, and M. Raynal presented a new and simple randomized signature-free binary consensus algorithm (denoted here MMR) that copes with the net effect of asynchrony Byzantine behaviors. Assuming message…
This work considers resilient, cooperative state estimation in unreliable multi-agent networks. A network of agents aims to collaboratively estimate the value of an unknown vector parameter, while an {\em unknown} subset of agents suffer…
This paper aims at jointly addressing two seemly conflicting issues in federated learning: differential privacy (DP) and Byzantine-robustness, which are particularly challenging when the distributed data are non-i.i.d. (independent and…
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…
This paper investigates the robustness of over-the-air federated learning to Byzantine attacks. The simple averaging of the model updates via over-the-air computation makes the learning task vulnerable to random or intended modifications of…
The success of machine learning (ML) has been intimately linked with the availability of large amounts of data, typically collected from heterogeneous sources and processed on vast networks of computing devices (also called {\em workers}).…
We consider a distributed reinforcement learning setting where multiple agents separately explore the environment and communicate their experiences through a central server. However, $\alpha$-fraction of agents are adversarial and can…
Modern networks assemble an ever growing number of nodes. However, it remains difficult to increase the number of channels per node, thus the maximal degree of the network may be bounded. This is typically the case in grid topology…
While being an effective framework of learning a shared model across multiple edge devices, federated learning (FL) is generally vulnerable to Byzantine attacks from adversarial edge devices. While existing works on FL mitigate such…
Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, but its robustness is threatened by Byzantine behaviors such as data and model poisoning. Existing defenses face fundamental…
Consider a distributed system with $n$ processors out of which $f$ can be Byzantine faulty. In the approximate agreement task, each processor $i$ receives an input value $x_i$ and has to decide on an output value $y_i$ such that - the…
In this paper, we investigate the problem of decentralized online resource allocation in the presence of Byzantine attacks. In this problem setting, some agents may be compromised due to external manipulations or internal failures, causing…