Byzantine resilience emerged as a prominent topic within the distributed machine learning community. Essentially, the goal is to enhance distributed optimization algorithms, such as …
M Xu, Z Zou, Y Cheng, Q Hu, D Yu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Decentralized learning involves training machine learning models over remote mobile devices, edge servers, or cloud servers while keeping data localized. Even though many …
Federated Learning (FL) offers innovative solutions for privacy-preserving collaborative machine learning (ML). Despite its promising potential, FL is vulnerable to various attacks …
We study\emph {Byzantine collaborative learning}, where $ n $ nodes seek to collectively learn from each others' local data. The data distribution may vary from one node to another …
Abstract Byzantine-resilient Stochastic Gradient Descent (SGD) aims at shielding model training from Byzantine faults, be they ill-labeled training datapoints, exploited …
Federated Learning (FL) enables many clients to train a joint model without sharing the raw data. While many byzantine-robust FL methods have been proposed, FL remains vulnerable …
To study the resilience of distributed learning, the “Byzantine" literature considers a strong threat model where workers can report arbitrary gradients to the parameter server. Whereas …
Multidimensional Approximate Agreement considers a setting of n parties, where each party holds a vector in ℝD as input. The honest parties are required to obtain very close outputs in …
Industry 5.0 is emerging as a result of the advancement in networking and communication technologies, artificial intelligence, distributed computing, and beyond 5G. Among the …