相关论文: PRISM-FCP: Byzantine-Resilient Federated Conformal…

In this paper, we consider a wireless federated inference scenario in which devices and a server share a pre-trained machine learning model. The devices communicate statistical information about their local data to the server over a common…

As the scale of federated learning (FL) systems expands, their inherent performance limitations like communication overhead, Byzantine vulnerability, and privacy leakage have become increasingly critical. This paper considers a personalized…

We study the problem of Byzantine fault tolerance in a distributed optimization setting, where there is a group of $N$ agents communicating with a trusted centralized coordinator. Among these agents, there is a subset of $f$ agents that may…

We demonstrate a deterministic Byzantine consensus algorithm with synchronous operation in partial synchrony. It is naturally leaderless, tolerates any number of $ f<n/2 $ Byzantine processes with 2 rounds of exchange of originator-only…

Federated learning (FL) is a privacy-friendly type of machine learning where devices locally train a model on their private data and typically communicate model updates with a server. In decentralized FL (DFL), peers communicate model…

Federated Learning (FL) emerged as a widely studied paradigm for distributed learning. Despite its many advantages, FL remains vulnerable to adversarial attacks, especially under data heterogeneity. We propose a new Byzantine-robust FL…

Ensuring resilience to Byzantine clients while maintaining the privacy of the clients' data is a fundamental challenge in federated learning (FL). When the clients' data is homogeneous, suitable countermeasures were studied from an…

Federated learning (FL) enables a set of geographically distributed clients to collectively train a model through a server. Classically, the training process is synchronous, but can be made asynchronous to maintain its speed in presence of…

We study distributed optimization in the presence of Byzantine adversaries, where both data and computation are distributed among $m$ worker machines, $t$ of which may be corrupt. The compromised nodes may collaboratively and arbitrarily…

Conformal prediction (CP) provides distribution-free, finite-sample coverage guarantees but critically relies on exchangeability, a condition often violated under distribution shift. We study the robustness of split conformal prediction…

Federated Learning (FL) enables multiple clients to collaboratively train models without sharing raw data, but is vulnerable to Byzantine attacks and data heterogeneity, which can severely degrade performance. Existing Byzantine-robust…

Robustness to Byzantine attacks is a necessity for various distributed training scenarios. When the training reduces to the process of solving a minimization problem, Byzantine robustness is relatively well-understood. However, other…

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…

The Weighted-Mean Subsequence Reduced (W-MSR) algorithm, the state-of-the-art method for Byzantine-resilient design of decentralized multi-robot systems, is based on discarding outliers received over Linear Consensus Protocol (LCP).…

Conformal prediction is widely adopted in uncertainty quantification, due to its post-hoc, distribution-free, and model-agnostic properties. In the realm of modern deep learning, researchers have proposed Feature Conformal Prediction (FCP),…

Modern distributed systems face growing security threats, as attackers continuously enhance their skills and vulnerabilities span across the entire system stack, from hardware to the application layer. In the system design phase, fault…

Privacy-preserving federated averaging is a central approach for protecting client privacy in federated learning. In this paper, we study this problem in an asynchronous communications setting with malicious aggregators. We propose a new…

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…

Population protocols model information spreading and computation in network systems where pairwise node exchanges are determined by an external random scheduler and nodes have small memory. Most of the population protocols in the literature…

Byzantine robustness is an essential feature of algorithms for certain distributed optimization problems, typically encountered in collaborative/federated learning. These problems are usually huge-scale, implying that communication…