15 citations · 47 across the 20 of their papers we have counts for
21 papers
Byzantine Machine Learning: MultiKrum and an optimal notion of robustness
Gilles Bareilles, Wassim Bouaziz, Julien Fageot +1
Aggregation rules are the cornerstone of distributed (or federated) learning in the presence of adversaries, under the so-called Byzantine threat model. They are also interesting m…
High-probability zeroth-order online convex optimisation beyond Euclidean geometry
David Janz, El-Mahdi El-Mhamdi, Arya Akhavan
We study online convex optimisation with -Lipschitz losses, -regularised FTRL, and randomised two-point finite-difference gradient estimators based on cone-measure…
Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
Wassim Bouaziz, Mathurin Videau, Nicolas Usunier +1
The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hid…
On Monotonicity in AI Alignment
Gilles Bareilles, Julien Fageot, Lê-Nguyên Hoang +4
Comparison-based preference learning has become central to the alignment of AI models with human preferences. However, these methods may behave counterintuitively. After empiricall…
The Strong, Weak and Benign Goodhart's law. An independence-free and paradigm-agnostic formalisation
Adrien Majka, El-Mahdi El-Mhamdi
Goodhart's law is a famous adage in policy-making that states that ``When a measure becomes a target, it ceases to be a good measure''. As machine learning models and the optimisat…
Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification
Wassim Bouaziz, El-Mahdi El-Mhamdi, Nicolas Usunier
Protecting the use of audio datasets is a major concern for data owners, particularly with the recent rise of audio deep learning models. While watermarks can be used to protect th…
On the Byzantine Fault Tolerance of signSGD with Majority Vote
Emanuele Mengoli, Luzius Moll, Virgilio Strozzi +1
In distributed learning, sign-based compression algorithms such as signSGD with majority vote provide a lightweight alternative to SGD with an additional advantage: fault tolerance…
A Case for Specialisation in Non-Human Entities
El-Mahdi El-Mhamdi, Lê-Nguyên Hoang, Mariame Tighanimine
With the rise of large multi-modal AI models, fuelled by recent interest in large language models (LLMs), the notion of artificial general intelligence (AGI) went from being restri…
Approaching the Harm of Gradient Attacks While Only Flipping Labels
Abdessamad El-Kabid, El-Mahdi El-Mhamdi
Machine learning systems deployed in distributed or federated environments are highly susceptible to adversarial manipulations, particularly availability attacks -- rendering the t…
Stop treating `AGI' as the north-star goal of AI research
Borhane Blili-Hamelin, Christopher Graziul, Leif Hancox-Li +13
The AI research community plays a vital role in shaping the scientific, engineering, and societal goals of AI research. In this position paper, we argue that focusing on the highly…
On Goodhart's law, with an application to value alignment
El-Mahdi El-Mhamdi, Lê-Nguyên Hoang
``When a measure becomes a target, it ceases to be a good measure'', this adage is known as {\it Goodhart's law}. In this paper, we investigate formally this law and prove that it…
Inverting Gradient Attacks Makes Powerful Data Poisoning
Wassim Bouaziz, El-Mahdi El-Mhamdi, Nicolas Usunier
Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in convex settings. The…
Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning
Wassim Bouaziz, Nicolas Usunier, El-Mahdi El-Mhamdi
Dataset ownership verification, the process of determining if a dataset is used in a model's training data, is necessary for detecting unauthorized data usage and data contaminatio…
Unravelling in Collaborative Learning
Aymeric Capitaine, Etienne Boursier, Antoine Scheid +4
Collaborative learning offers a promising avenue for leveraging decentralized data. However, collaboration in groups of strategic learners is not a given. In this work, we consider…
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…
Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments
Lê-Nguyên Hoang, Louis Faucon, Aidan Jungo +13
Today's large-scale algorithms have become immensely influential, as they recommend and moderate the content that billions of humans are exposed to on a daily basis. They are the d…
On the Strategyproofness of the Geometric Median
El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui +1
The geometric median, an instrumental component of the secure machine learning toolbox, is known to be effective when robustly aggregating models (or gradients), gathered from pote…
Garfield: System Support for Byzantine Machine Learning
Rachid Guerraoui, Arsany Guirguis, Jérémy Max Plassmann +2
We present Garfield, a library to transparently make machine learning (ML) applications, initially built with popular (but fragile) frameworks, e.g., TensorFlow and PyTorch, Byzant…
Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning)
El-Mahdi El-Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui +3
We study Byzantine collaborative learning, where nodes seek to collectively learn from each others' local data. The data distribution may vary from one node to another. No node…
Distributed Momentum for Byzantine-resilient Learning
El-Mahdi El-Mhamdi, Rachid Guerraoui, Sébastien Rouault
Momentum is a variant of gradient descent that has been proposed for its benefits on convergence. In a distributed setting, momentum can be implemented either at the server or the…
Fast and Robust Distributed Learning in High Dimension
El-Mahdi El-Mhamdi, Rachid Guerraoui, Sébastien Rouault
Could a gradient aggregation rule (GAR) for distributed machine learning be both robust and fast? This paper answers by the affirmative through multi-Bulyan. Given workers, …