Related papers: Distributed Detection in Tree Topologies with Byza…
As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with…
Multi-task learning is an effective way to address the challenge of model personalization caused by high data heterogeneity in federated learning. However, extending multi-task learning to the online decentralized federated learning setting…
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…
We study local stochastic gradient descent methods for solving federated optimization over a network of agents communicating indirectly through a centralized coordinator. We are interested in the Byzantine setting where there is a subset of…
This paper proposes a Robust Gradient Classification Framework (RGCF) for Byzantine fault tolerance in distributed stochastic gradient descent. The framework consists of a pattern recognition filter which we train to be able to classify…
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,…
Existing protocols for byzantine fault tolerant distributed systems usually rely on the correct agents' ability to detect faulty agents and/or to detect the occurrence of some event or action on some correct agent. In this paper, we provide…
We consider a distributed reinforcement learning setting where multiple agents separately explore the environment and communicate their experiences through a central server. However, $\alpha$-fraction of agents are adversarial and can…
Achieving agreement among distributed parties is a fundamental task in modern systems, underpinning applications such as consensus in blockchains, coordination in cloud infrastructure, and fault tolerance in critical services. However, this…
Byzantine Fault Tolerant (BFT) systems are considered by the systems research community to be state of the art with regards to providing reliability in distributed systems. BFT systems provide safety and liveness guarantees with reasonable…
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 $n$…
Distributed learning has become a promising computational parallelism paradigm that enables a wide scope of intelligent applications from the Internet of Things (IoT) to autonomous driving and the healthcare industry. This paper studies…
The alternating direction of multipliers method (ADMM) is a popular method to solve distributed consensus optimization utilizing efficient communication among various nodes in the network. However, in the presence of faulty or attacked…
This work considers two related learning problems in a federated attack prone setting: federated principal components analysis (PCA) and federated low rank column-wise sensing (LRCS). The node attacks are assumed to be Byzantine which means…
We explore the correctness of the Certified Propagation Algorithm (CPA) [6, 1, 8, 5] in solving broadcast with locally bounded Byzantine faults. CPA allows the nodes to use only local information regarding the network topology. We provide a…
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…
Distributed control systems require high reliability and availability guarantees despite often being deployed at the edge of network infrastructure. Edge computing resources are less secure and less reliable than centralized resources in…
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…
In this work, we consider the distributed stochastic optimization problem of minimizing a non-convex function $f(x) = \mathbb{E}_{\xi \sim \mathcal{D}} f(x; \xi)$ in an adversarial setting, where the individual functions $f(x; \xi)$ can…
Most existing Byzantine-robust federated learning (FL) methods suffer from slow and unstable convergence. Moreover, when handling a substantial proportion of colluded malicious clients, achieving robustness typically entails compromising…