Related papers: Asymptotic Analysis of Distributed Bayesian Detect…
This paper introduces a deep learning-based framework for resilient decision fusion in adversarial multi-sensor networks, providing a unified mathematical setup that encompasses diverse scenarios, including varying Byzantine node…
All practical applications contain some degree of nondeterminism. When such applications are replicated to achieve Byzantine fault tolerance (BFT), their nondeterministic operations must be controlled to ensure replica consistency. To the…
Consider a synchronous point-to-point network of n nodes connected by directed links, wherein each node has a binary input. This paper proves a tight necessary and sufficient condition on the underlying communication topology for achieving…
This report considers the problem of Byzantine fault-tolerance in synchronous parallelized learning that is founded on the parallelized stochastic gradient descent (parallelized-SGD) algorithm. The system comprises a master, and $n$…
In this paper, we propose a class of robust stochastic subgradient methods for distributed learning from heterogeneous datasets at presence of an unknown number of Byzantine workers. The Byzantine workers, during the learning process, may…
In many modern applications, large-scale sensor networks are used to perform statistical inference tasks. In this paper, we propose Bayesian methods for multiple change-point detection using a sensor network in which a fusion center (FC)…
This paper presents Twins, an automated unit test generator of Byzantine attacks. Twins implements three types of Byzantine behaviors: (i) leader equivocation, (ii) double voting, and (iii) losing internal state such as forgetting 'locks'…
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…
In this paper, we propose a locally optimum detection (LOD) scheme for detecting a weak radioactive source buried in background clutter. We develop a decentralized algorithm, based on alternating direction method of multipliers (ADMM), for…
Consider an asynchronous network in a shared-memory environment consisting of n nodes. Assume that up to f of the nodes might be Byzantine (n > 12f), where the adversary is full-information and dynamic (sometimes called adaptive). In…
Distributed Federated Learning (DFL) enables decentralized model training across large-scale systems without a central parameter server. However, DFL faces three critical challenges: privacy leakage from honest-but-curious neighbors, slow…
This paper introduces a deterministic Byzantine consensus algorithm that relies on a new weak coordinator. As opposed to previous algorithms that cannot terminate in the presence of a faulty or slow coordinator, our algorithm can terminate…
In this paper, a fully distributed averaging algorithm in the presence of adversarial Byzantine agents is proposed. The algorithm is based on a resilient retrieval procedure, where all non-Byzantine nodes send their own initial values and…
We study a distributed computation problem in the presence of Byzantine workers where a central node wishes to solve a task that is divided into independent sub-tasks, each of which needs to be solved correctly. The distributed computation…
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 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…
With the rapid development of blockchain and its applications, the amount of data stored on decentralized storage networks (DSNs) has grown exponentially. DSNs bring together affordable storage resources from around the world to provide…
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…
Byzantine agreement is a fundamental problem in fault-tolerant distributed networks that has been studied intensively for the last four decades. Most of these works designed protocols for complete networks. A key goal in Byzantine protocols…
Decentralized federated learning (DFL) enables collaborative model training without centralized trust, but it remains vulnerable to Byzantine clients that poison gradients under heterogeneous (Non-IID) data. Existing defenses face a…