相关论文: Defending Against Saddle Point Attack in Byzantine…

In centralized settings, it is well known that stochastic gradient descent (SGD) avoids saddle points and converges to local minima in nonconvex problems. However, similar guarantees are lacking for distributed first-order algorithms. The…

Recently, decentralized learning has emerged as a popular peer-to-peer signal and information processing paradigm that enables model training across geographically distributed agents in a scalable manner, without the presence of any central…

Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper,…

This paper considers the problem of resilient distributed optimization and stochastic machine learning in a server-based architecture. The system comprises a server and multiple agents, where each agent has a local cost function. The agents…

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 paper, we study a linear bandit optimization problem in a federated setting where a large collection of distributed agents collaboratively learn a common linear bandit model. Standard federated learning algorithms applied to this…

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 distributed learning, a central server trains a model according to updates provided by nodes holding local data samples. In the presence of one or more malicious servers sending incorrect information (a Byzantine adversary), standard…

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…

Communication between workers and the master node to collect local stochastic gradients is a key bottleneck in a large-scale federated learning system. Various recent works have proposed to compress the local stochastic gradients to…

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,…

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…

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 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…

In this paper, we investigate the challenging framework of Byzantine-robust training in distributed machine learning (ML) systems, focusing on enhancing both efficiency and practicality. As distributed ML systems become integral for complex…

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,…

Recent focus on robustness to adversarial attacks for deep neural networks produced a large variety of algorithms for training robust models. Most of the effective algorithms involve solving the min-max optimization problem for training…

In Federated Reinforcement Learning (FRL), agents aim to collaboratively learn a common task, while each agent is acting in its local environment without exchanging raw trajectories. Existing approaches for FRL either (a) do not provide any…

Jointly addressing Byzantine attacks and privacy leakage in distributed machine learning (DML) has become an important issue. A common strategy involves integrating Byzantine-resilient aggregation rules with differential privacy mechanisms.…

This paper focuses on decentralized stochastic optimization in the presence of Byzantine attacks. During the optimization process, an unknown number of malfunctioning or malicious workers, termed as Byzantine workers, disobey the…