Salvato in:
Dettagli Bibliografici
Autori principali: Molodtsov, Gleb, Medyakov, Daniil, Skorik, Sergey, Khachaturov, Nikolas, Tigranyan, Shahane, Aletov, Vladimir, Avetisyan, Aram, Takáč, Martin, Beznosikov, Aleksandr
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.07614
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918230605430784
author Molodtsov, Gleb
Medyakov, Daniil
Skorik, Sergey
Khachaturov, Nikolas
Tigranyan, Shahane
Aletov, Vladimir
Avetisyan, Aram
Takáč, Martin
Beznosikov, Aleksandr
author_facet Molodtsov, Gleb
Medyakov, Daniil
Skorik, Sergey
Khachaturov, Nikolas
Tigranyan, Shahane
Aletov, Vladimir
Avetisyan, Aram
Takáč, Martin
Beznosikov, Aleksandr
contents Recent advancements in machine learning have improved performance while also increasing computational demands. While federated and distributed setups address these issues, their structures remain vulnerable to malicious influences. In this paper, we address a specific threat: Byzantine attacks, wherein compromised clients inject adversarial updates to derail global convergence. We combine the concept of trust scores with trial function methodology to dynamically filter outliers. Our methods address the critical limitations of previous approaches, allowing operation even when Byzantine nodes are in the majority. Moreover, our algorithms adapt to widely used scaled methods such as Adam and RMSProp, as well as practical scenarios, including local training and partial participation. We validate the robustness of our methods by conducting extensive experiments on both public datasets and private ECG data collected from medical institutions. Furthermore, we provide a broad theoretical analysis of our algorithms and their extensions to the aforementioned practical setups. The convergence guaranties of our methods are comparable to those of classical algorithms developed without Byzantine interference.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07614
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bant: Byzantine Antidote via Trial Function and Trust Scores
Molodtsov, Gleb
Medyakov, Daniil
Skorik, Sergey
Khachaturov, Nikolas
Tigranyan, Shahane
Aletov, Vladimir
Avetisyan, Aram
Takáč, Martin
Beznosikov, Aleksandr
Machine Learning
Optimization and Control
Recent advancements in machine learning have improved performance while also increasing computational demands. While federated and distributed setups address these issues, their structures remain vulnerable to malicious influences. In this paper, we address a specific threat: Byzantine attacks, wherein compromised clients inject adversarial updates to derail global convergence. We combine the concept of trust scores with trial function methodology to dynamically filter outliers. Our methods address the critical limitations of previous approaches, allowing operation even when Byzantine nodes are in the majority. Moreover, our algorithms adapt to widely used scaled methods such as Adam and RMSProp, as well as practical scenarios, including local training and partial participation. We validate the robustness of our methods by conducting extensive experiments on both public datasets and private ECG data collected from medical institutions. Furthermore, we provide a broad theoretical analysis of our algorithms and their extensions to the aforementioned practical setups. The convergence guaranties of our methods are comparable to those of classical algorithms developed without Byzantine interference.
title Bant: Byzantine Antidote via Trial Function and Trust Scores
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2505.07614