Publication

The Hidden Vulnerability of Distributed Learning in Byzantium

Rachid Guerraoui, El Mahdi El Mhamdi, Sébastien Louis Alexandre Rouault
2018
Conference Papers

Abstract

While machine learning is going through an era of celebrated success, concerns have been raised about the vulnerability of its backbone: stochastic gradient descent (SGD). Recent approaches have been proposed to ensure the robustness of distributed SGD against adversarial (Byzantine) workers sending \emph{poisoned} gradients during the training phase. Some of these approaches have been proven \emph{Byzantine--resilient}: they ensure the \emph{convergence} of SGD despite the presence of a minority of adversarial workers. We show in this paper that \emph{convergence is not enough}. In high dimension $d \gg 1$ , an adver-sary can build on the loss function's non--convexity to make SGD converge to \emph{ineffective} models. More precisely, we bring to light that existing Byzantine--resilient schemes leave a \emph{margin of poisoning} of $\bigOmega\left(f(d)\right)$ , where $f(d)$ increases at least like $\sqrt{d}$ . Based on this \emph{leeway}, we build a simple attack, and experimentally show its strong to utmost effectivity on CIFAR--10 and MNIST. We introduce \emph{Bulyan}, and prove it significantly reduces the attacker's leeway to a narrow $\bigO\,( \sfrac{1}{\sqrt{d~}})$ bound. We empirically show that Bulyan does not suffer the fragility of existing aggregation rules and, at a reasonable cost in terms of required batch size, achieves convergence \emph{as if} only non--Byzantine gradients had been used to update the model.

Official source

https://infoscience.epfl.ch/entities/publication/c0dbc83d-6b3a-4a27-8f3f-fc87ece4c452

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Rachid Guerraoui, El Mahdi El Mhamdi, Sébastien Louis Alexandre Rouault
2018
Conference Papers

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/c0dbc83d-6b3a-4a27-8f3f-fc87ece4c452

About this result

Related concepts (32)

Machine learning

Machine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.

TensorFlow

TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks. TensorFlow was developed by the Google Brain team for internal Google use in research and production. The initial version was released under the Apache License 2.0 in 2015. Google released the updated version of TensorFlow, named TensorFlow 2.0, in September 2019.

Byzantine Empire

The Byzantine Empire, also referred to as the Eastern Roman Empire, was the continuation of the Roman Empire primarily in its eastern provinces during Late Antiquity and the Middle Ages, when its capital city was Constantinople. It survived the fall of the Western Roman Empire in the 5th century AD and continued to exist until the fall of Constantinople to the Ottoman Empire in 1453. During most of its existence, the empire remained the most powerful economic, cultural, and military force in the Mediterranean world.

Related publications (30)

Random matrix methods for high-dimensional machine learning models

Antoine Philippe Michel Bodin

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

EPFL2024

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Anastasiia Koloskova

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

EPFL2024

Understanding generalization and robustness in modern deep learning

Maksym Andriushchenko

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

EPFL2024