相关论文: MixTailor: Mixed Gradient Aggregation for Robust L…

State-of-the-art machine learning models are routinely trained on large-scale distributed clusters. Crucially, such systems can be compromised when some of the computing devices exhibit abnormal (Byzantine) behavior and return arbitrary…

Federated learning systems that jointly preserve Byzantine robustness and privacy have remained an open problem. Robust aggregation, the standard defense for Byzantine attacks, generally requires server access to individual updates or…

In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication constraints. While prior work has developed various robust aggregation rules at the server to enhance robustness to Byzantine…

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 a global model without sharing their local data. Recent studies have highlighted the vulnerability of FL to Byzantine attacks, where malicious clients send poisoned…

In machine learning security, one is often faced with the problem of removing outliers from a given set of high-dimensional vectors when computing their average. For example, many variants of data poisoning attacks produce gradient vectors…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Training modern neural networks or models typically requires averaging over a sample of high-dimensional vectors. Poisoning attacks can skew or bias the average vectors used to train the model, forcing the model to learn specific patterns…

In this paper, we propose a robust aggregation method for federated learning (FL) that can effectively tackle malicious Byzantine attacks. At each user, model parameter is firstly updated by multiple steps, which is adjustable over…

In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have been proposed at the central server to mitigate the impact of…

This paper jointly considers privacy preservation and Byzantine-robustness in decentralized learning. In a decentralized network, honest-but-curious agents faithfully follow the prescribed algorithm, but expect to infer their neighbors'…

In this work, we consider the resilience of distributed algorithms based on stochastic gradient descent (SGD) in distributed learning with potentially Byzantine attackers, who could send arbitrary information to the parameter server to…

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…

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…

Distributed model training is vulnerable to byzantine system failures and adversarial compute nodes, i.e., nodes that use malicious updates to corrupt the global model stored at a parameter server (PS). To guarantee some form of robustness,…

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…

We propose two novel stochastic gradient descent algorithms, ByGARS and ByGARS++, for distributed machine learning in the presence of any number of Byzantine adversaries. In these algorithms, reputation scores of workers are computed using…

We propose a novel robust aggregation rule for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the…

Recent advances in large-scale distributed learning algorithms have enabled communication-efficient training via SignSGD. Unfortunately, a major issue continues to plague distributed learning: namely, Byzantine failures may incur serious…

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…