35 citations · 148 across the 31 of their papers we have counts for
25 papers · 1 filter
Byzantine-Robust Federated Representation Learning
Leonardo F. Toso, James Anderson, Rafael Pinot +1
We study federated learning (FL) with adversarial clients, where the goal is to minimize the average loss of the honest (non-adversarial) clients without knowing their identity. Un…
Robust Federated Inference
Akash Dhasade, Sadegh Farhadkhani, Rachid Guerraoui +4
Federated inference, in the form of one-shot federated learning, edge ensembles, or federated ensembles, has emerged as an attractive solution to combine predictions from multiple…
ByzFL: Research Framework for Robust Federated Learning
Marc González, Rachid Guerraoui, Rafael Pinot +3
We present ByzFL, an open-source Python library for developing and benchmarking robust federated learning (FL) algorithms. ByzFL provides a unified and extensible framework that in…
Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory
Lucas Gnecco-Heredia, Matteo Sammut, Muni Sreenivas Pydi +3
Randomization as a mean to improve the adversarial robustness of machine learning models has recently attracted significant attention. Unfortunately, much of the theoretical analys…
Revisiting Ensembling in One-Shot Federated Learning
Youssef Allouah, Akash Dhasade, Rachid Guerraoui +5
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 signi…
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
Youssef Allouah, Abdellah El Mrini, Rachid Guerraoui +2
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 heteroge…
Overcoming the Challenges of Batch Normalization in Federated Learning
Rachid Guerraoui, Rafael Pinot, Geovani Rizk +2
Batch normalization has proven to be a very beneficial mechanism to accelerate the training and improve the accuracy of deep neural networks in centralized environments. Yet, the s…
On the Relevance of Byzantine Robust Optimization Against Data Poisoning
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta +1
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…
Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
Youssef Allouah, Sadegh Farhadkhani, Rachid GuerraouI +4
The possibility of adversarial (a.k.a., {\em Byzantine}) clients makes federated learning (FL) prone to arbitrary manipulation. The natural approach to robustify FL against adversa…
SABLE: Secure And Byzantine robust LEarning
Antoine Choffrut, Rachid Guerraoui, Rafael Pinot +3
Due to the widespread availability of data, machine learning (ML) algorithms are increasingly being implemented in distributed topologies, wherein various nodes collaborate to trai…
Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity
Youssef Allouah, Sadegh Farhadkhani, Rachid Guerraoui +3
Byzantine machine learning (ML) aims to ensure the resilience of distributed learning algorithms to misbehaving (or Byzantine) machines. Although this problem received significant…
On the Privacy-Robustness-Utility Trilemma in Distributed Learning
Youssef Allouah, Rachid Guerraoui, Nirupam Gupta +2
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 adversari…
On the Impossible Safety of Large AI Models
El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui +5
Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance. However they have been empirically found to pos…
Robust Collaborative Learning with Linear Gradient Overhead
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta +3
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…
Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis
Raphael Ettedgui, Alexandre Araujo, Rafael Pinot +2
Randomized smoothing is the dominant standard for provable defenses against adversarial examples. Nevertheless, this method has recently been proven to suffer from important inform…
Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta +2
Byzantine resilience emerged as a prominent topic within the distributed machine learning community. Essentially, the goal is to enhance distributed optimization algorithms, such a…
Towards Consistency in Adversarial Classification
Laurent Meunier, Raphaël Ettedgui, Rafael Pinot +2
In this paper, we study the problem of consistency in the context of adversarial examples. Specifically, we tackle the following question: can surrogate losses still be used as a p…
Combining Differential Privacy and Byzantine Resilience in Distributed SGD
Rachid Guerraoui, Nirupam Gupta, Rafael Pinot +2
Privacy and Byzantine resilience (BR) are two crucial requirements of modern-day distributed machine learning. The two concepts have been extensively studied individually but the q…
On the robustness of randomized classifiers to adversarial examples
Rafael Pinot, Laurent Meunier, Florian Yger +3
This paper investigates the theory of robustness against adversarial attacks. We focus on randomized classifiers (\emph{i.e.} classifiers that output random variables) and provide…
Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
Rachid Guerraoui, Nirupam Gupta, Rafaël Pinot +2
This paper addresses the problem of combining Byzantine resilience with privacy in machine learning (ML). Specifically, we study if a distributed implementation of the renowned Sto…
Advocating for Multiple Defense Strategies against Adversarial Examples
Alexandre Araujo, Laurent Meunier, Rafael Pinot +1
It has been empirically observed that defense mechanisms designed to protect neural networks against adversarial examples offer poor performance against adve…
Randomization matters. How to defend against strong adversarial attacks
Rafael Pinot, Raphael Ettedgui, Geovani Rizk +2
Is there a classifier that ensures optimal robustness against all adversarial attacks? This paper answers this question by adopting a game-theoretic point of view. We show that adv…
A unified view on differential privacy and robustness to adversarial examples
Rafael Pinot, Florian Yger, Cédric Gouy-Pailler +1
This short note highlights some links between two lines of research within the emerging topic of trustworthy machine learning: differential privacy and robustness to adversarial ex…
Robust Neural Networks using Randomized Adversarial Training
Alexandre Araujo, Laurent Meunier, Rafael Pinot +1
This paper tackles the problem of defending a neural network against adversarial attacks crafted with different norms (in particular and bounded adversarial…