Publications by Rafaël Benjamin Pinot

Robust Machine Learning - Distributed Methods for Safe AI

Rachid Guerraoui, Nirupam Gupta, Rafaël Benjamin Pinot

Today, machine learning algorithms are often distributed across multiple machines to leverage more computing power and more data. However, the use of a distributed framework entails a variety of security threats. In particular, some of the machines may mis ...

Springer2024

Revisiting Ensembling in One-Shot Federated Learning

Rachid Guerraoui, Anne-Marie Kermarrec, Rafael Pereira Pires, Youssef Allouah, Akash Balasaheb Dhasade, Rishi Sharma, Nirupam Gupta, Rafaël Benjamin Pinot

Federated learning (FL) is an appealing approach to training machine learning models without sharing raw data. However, standard FL algorithms are iterative and thus induce a significant communication cost. One-shot federated learning (OFL) trades the iter ...

Curran Associates, Inc.2024

Brief Announcement: A Case for Byzantine Machine Learning

Rachid Guerraoui, Sadegh Farhadkhani, Nirupam Gupta, Rafaël Benjamin Pinot

The success of machine learning (ML) has been intimately linked with the availability of large amounts of data, typically collected from heterogeneous sources and processed on vast networks of computing devices (also called workers). Beyond accuracy, the u ...

ACM2024

Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients

Rachid Guerraoui, Youssef Allouah, Nirupam Gupta, Rafaël Benjamin Pinot

Federated learning (FL) is an appealing paradigm that allows a group of machines (a.k.a. clients) to learn collectively while keeping their data local. However, due to the heterogeneity between the clients' data distributions, the model obtained through th ...

Neural information processing systems foundation2024

Byzantine Machine Learning: A Primer

Rachid Guerraoui, Nirupam Gupta, Rafaël Benjamin Pinot

The problem of Byzantine resilience in distributed machine learning, a.k.a., Byzantine machine learning, consists in designing distributed algorithms that can train an accurate model despite the presence of Byzantine nodes, i.e., nodes with corrupt data or ...

2023

On the Privacy-Robustness-Utility Trilemma in Distributed Learning

Rachid Guerraoui, John Stephan, Youssef Allouah, Nirupam Gupta, Rafaël Benjamin Pinot

The ubiquity of distributed machine learning (ML) in sensitive public domain applications calls for algorithms that protect data privacy, while being robust to faults and adversarial behaviors. Although privacy and robustness have been extensively studied ...

2023

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

Rachid Guerraoui, Youssef Allouah, Geovani Rizk, Nirupam Gupta, Rafaël Benjamin Pinot

The theory underlying robust distributed learning algorithms, designed to resist adversarial machines, matches empirical observations when data is homogeneous. Under data heterogeneity however, which is the norm in practical scenarios, established lower bo ...

2023

Robust Collaborative Learning with Linear Gradient Overhead

Rachid Guerraoui, John Stephan, Sadegh Farhadkhani, Le Nguyen Hoang, Nirupam Gupta, Rafaël Benjamin Pinot

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

PLMR2023

Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity

Rachid Guerraoui, John Stephan, Sadegh Farhadkhani, Youssef Allouah, Nirupam Gupta, Rafaël Benjamin Pinot

Byzantine machine learning (ML) aims to ensure the resilience of distributed learning algorithms to misbehaving (or Byzantine) machines. Although this problem received significant attention, prior works often assume the data held by the machines to be homo ...

PMLR2023

The Universal Gossip Fighter

Rachid Guerraoui, Anne-Marie Kermarrec, Anastasiia Kucherenko, Rafaël Benjamin Pinot

The notion of adversary is a staple of distributed computing. An adversary typically models “hostile” assumptions about the underlying distributed environment, e.g., a network that can drop messages, an operating system that can delay processes or an attac ...

IEEE2022