相关论文: Federated Learning Resilient to Byzantine Attacks …

Federated learning (FL) is designed to preserve data privacy during model training, where the data remains on the client side (i.e., IoT devices), and only model updates of clients are shared iteratively for collaborative learning. However,…

Federated Learning (FL) enables decentralized model training without sharing raw data. However, it remains vulnerable to Byzantine attacks, which can compromise the aggregation of locally updated parameters at the central server.…

The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among many vulnerabilities, the risk of Byzantine attacks is of…

Byzantine-robust distributed optimization relies on robust aggregation rules to mitigate the influence of malicious Byzantine workers. Despite the proliferation of such rules, a unified convergence analysis framework that accommodates…

Federated Learning (FL) enables heterogeneous clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy. However, gradients and model updates can still leak sensitive…

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…

Distributed optimization with open collaboration is a popular field since it provides an opportunity for small groups/companies/universities, and individuals to jointly solve huge-scale problems. However, standard optimization algorithms…

With the increasing importance of machine learning, the privacy and security of training data have become critical. Federated learning, which stores data in distributed nodes and shares only model parameters, has gained significant…

In vehicle edge computing (VEC), asynchronous federated learning (AFL) is used, where the edge receives a local model and updates the global model, effectively reducing the global aggregation latency.Due to different amounts of local…

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…

Byzantine robustness has received significant attention recently given its importance for distributed and federated learning. In spite of this, we identify severe flaws in existing algorithms even when the data across the participants is…

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…

Standard federated learning algorithms are vulnerable to adversarial nodes, a.k.a. Byzantine failures. To solve this issue, robust distributed learning algorithms have been developed, which typically replace parameter averaging by robust…

Federated Learning (FL) aims to train a collaborative model while preserving data privacy. However, the distributed nature of this approach still raises privacy and security issues, such as the exposure of sensitive data due to inference…

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)…

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and…

One of the most common defense strategies against Byzantine clients in federated learning (FL) is to employ a robust aggregator mechanism that makes the training more resilient. While many existing Byzantine robust aggregators provide…

We study local stochastic gradient descent methods for solving federated optimization over a network of agents communicating indirectly through a centralized coordinator. We are interested in the Byzantine setting where there is a subset of…

Federated learning (FL), an emerging distributed machine learning paradigm, has been applied to various privacy-preserving scenarios. However, due to its distributed nature, FL faces two key issues: the non-independent and identical…

This paper studies Byzantine-robust stochastic optimization over a decentralized network, where every agent periodically communicates with its neighbors to exchange local models, and then updates its own local model by stochastic gradient…