Related papers: Practical Validity Conditions for Byzantine-Tolera…

It is generally believed that ensemble approaches, which combine multiple algorithms or models, can outperform any single algorithm at machine learning tasks, such as prediction. In this paper, we propose Bayesian convex and linear…

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…

Byzantine Agreement (BA) considers a setting of $n$ parties, out of which up to $t$ can exhibit byzantine (malicious) behavior. Honest parties must decide on a common value (agreement), which must belong to a set determined by the honest…

Federated learning (FL) has recently become a hot research topic, in which Byzantine robustness, communication efficiency and privacy preservation are three important aspects. However, the tension among these three aspects makes it hard to…

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…

This paper studies the Byzantine Agreement problem where the nodes have access to a predictor that flags nodes for suspicion of faulty (Byzantine) behavior. We focus on algorithmic resilience -- the maximum number of faulty nodes an…

The possibility of adversarial (a.k.a., {\em Byzantine}) clients makes federated learning (FL) prone to arbitrary manipulation. The natural approach to robustify FL against adversarial clients is to replace the simple averaging operation at…

Partial participation is essential for communication-efficient federated learning at scale, yet existing Byzantine-robust methods typically assume full client participation. In the partial participation setting, a majority of the sampled…

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,…

This paper proposes a Byzantine-resilient consensus framework that simultaneously pursues two tightly coupled objectives: actively identifying Byzantine agents and guaranteeing resilient consensus among normal agents. Unlike existing…

Strong replica consistency is often achieved by writing deterministic applications, or by using a variety of mechanisms to render replicas deterministic. There exists a large body of work on how to render replicas deterministic under the…

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…

Approximate Agreement ($\mathcal{AA}$) is a fundamental primitive that, even in the presence of Byzantine faults, allows honest parties to obtain close (but not necessarily identical) outputs that lie within the range of their inputs. While…

Due to the emergent adoption of distributed systems when building applications, demand for reliability and availability has increased. These properties can be achieved through replication techniques using middleware algorithms that must be…

Federated learning (FL) enables multiple clients to collaboratively train an accurate global model while protecting clients' data privacy. However, FL is susceptible to Byzantine attacks from malicious participants. Although the problem has…

Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers. Such misbehaviors are commonly modeled as Byzantine failures, allowing arbitrarily corrupted communication, or as data…

Federated learning (FL) facilitates distributed training across different IoT and edge devices, safeguarding the privacy of their data. The inherent distributed structure of FL introduces vulnerabilities, especially from adversarial devices…

Federated reinforcement learning (FRL) allows agents to jointly learn a global decision-making policy under the guidance of a central server. While FRL has advantages, its decentralized design makes it prone to poisoning attacks. To…

The ability to perform repeated Byzantine agreement lies at the heart of important applications such as blockchain price oracles or replicated state machines. Any such protocol requires the following properties: (1) \textit{Byzantine…

Much of the past work on asynchronous approximate Byzantine consensus has assumed scalar inputs at the nodes [3, 7]. Recent work has yielded approximate Byzantine consensus algorithms for the case when the input at each node is a…