Related papers: Byzantine-Resilient Decentralized Online Resource …
Service replication distributes an application over many processes for tolerating faults, attacks, and misbehavior among a subset of the processes. The established state-machine replication paradigm inherently requires the application to be…
This paper deals with distributed finite-sum optimization for learning over networks in the presence of malicious Byzantine attacks. To cope with such attacks, most resilient approaches so far combine stochastic gradient descent (SGD) with…
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…
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…
Detection and mitigation of Byzantine behaviors in a decentralized learning setting is a daunting task, especially when the data distribution at the users is heterogeneous. As our main contribution, we propose Basil, a fast and…
Numerous distributed tasks have to be handled in a setting where a fraction of nodes behaves Byzantine, that is, deviates arbitrarily from the intended protocol. Resilient, deterministic protocols rely on the detection of majorities 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…
This paper aims to solve a distributed learning problem under Byzantine attacks. In the underlying distributed system, a number of unknown but malicious workers (termed as Byzantine workers) can send arbitrary messages to the master and…
Self-stabilization is a versatile approach to fault-tolerance since it permits a distributed system to recover from any transient fault that arbitrarily corrupts the contents of all memories in the system. Byzantine tolerance is an…
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…
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…
This paper considers the problem of Byzantine fault-tolerance in distributed multi-agent optimization. In this problem, each agent has a local cost function, and in the fault-free case, the goal is to design a distributed algorithm that…
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…
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.…
Machine Learning (ML) solutions are nowadays distributed, according to the so-called server/worker architecture. One server holds the model parameters while several workers train the model. Clearly, such architecture is prone to various…
Decentralized machine learning (DL) has been receiving an increasing interest recently due to the elimination of a single point of failure, present in Federated learning setting. Yet, it is threatened by the looming threat of Byzantine…
We investigate the distributed online economic dispatch problem for power systems with time-varying coupled inequality constraints. The problem is formulated as a distributed online optimization problem in a multi-agent system. At each time…
This paper proposes the first implementation of an atomic storage tolerant to mobile Byzantine agents. Our implementation is designed for the round-based synchronous model where the set of Byzantine nodes changes from round to round. In…
Inherent client drifts caused by data heterogeneity, as well as vulnerability to Byzantine attacks within the system, hinder effective model training and convergence in federated learning (FL). This paper presents two new frameworks, named…
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…