activity
20192026
most citedOn the Impossible Safety of Large AI Models

8 citations · 22 across the 17 of their papers we have counts for

collaborators

21 papers

stat.ML2026★ 1 cited

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…

cs.LG2025

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…

cs.CR2025

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…

math.ST2025

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…

stat.ML2025

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…

cs.CR2025

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…