相关论文: Byzantine-robust Federated Learning through Collab…

Federated learning has arisen as a mechanism to allow multiple participants to collaboratively train a model without sharing their data. In these settings, participants (workers) may not trust each other fully; for instance, a set of…

Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased…

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…

In federated learning (FL), profiling and verifying each client is inherently difficult, which introduces a significant security vulnerability: malicious clients, commonly referred to as Byzantines, can degrade the accuracy of the global…

Federated learning is a distributed training framework vulnerable to Byzantine attacks, particularly when over 50% of clients are malicious or when datasets are highly non-independent and identically distributed (non-IID). Additionally,…

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust…

Byzantine attacks hinder the deployment of federated learning algorithms. Although we know that the benign gradients and Byzantine attacked gradients are distributed differently, to detect the malicious gradients is challenging due to (1)…

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…

We consider the federated learning problem where data on workers are not independent and identically distributed (i.i.d.). During the learning process, an unknown number of Byzantine workers may send malicious messages to the central node,…

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,…

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…

To study the resilience of distributed learning, the "Byzantine" literature considers a strong threat model where workers can report arbitrary gradients to the parameter server. Whereas this model helped obtain several fundamental results,…

Training of large scale models on distributed clusters is a critical component of the machine learning pipeline. However, this training can easily be made to fail if some workers behave in an adversarial (Byzantine) fashion whereby they…

This paper addresses federated learning (FL) in the context of malicious Byzantine attacks and data heterogeneity. We introduce a novel Robust Average Gradient Algorithm (RAGA), which uses the geometric median for aggregation and {allows…

Federated learning is a newly emerging distributed learning framework that facilitates the collaborative training of a shared global model among distributed participants with their privacy preserved. However, federated learning systems are…

Federated Learning (FL) enables multiple clients to collaboratively train models without sharing raw data, but is vulnerable to Byzantine attacks and data heterogeneity, which can severely degrade performance. Existing Byzantine-robust…

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 Learning (FL) thrives in training a global model with numerous clients by only sharing the parameters of their local models trained with their private training datasets. Therefore, without revealing the private dataset, the…

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…

A plethora of modern machine learning tasks require the utilization of large-scale distributed clusters as a critical component of the training pipeline. However, abnormal Byzantine behavior of the worker nodes can derail the training and…