collaborators

7 papers

cs.CR2025

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…

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…

cs.AI2025

Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights

Mathieu Andreux, Breno Baldas Skuk, Hamza Benchekroun +41

We present Surfer-H, a cost-efficient web agent that integrates Vision-Language Models (VLM) to perform user-defined tasks on the web. We pair it with Holo1, a new open-weight coll…

cs.CL2025

Dialect Normalization using Large Language Models and Morphological Rules

Antonios Dimakis, John Pavlopoulos, Antonios Anastasopoulos

Natural language understanding systems struggle with low-resource languages, including many dialects of high-resource ones. Dialect-to-standard normalization attempts to tackle thi…

cs.CL2025

When Every Token Counts: Optimal Segmentation for Low-Resource Language Models

Bharath Raj, Garvit Suri, Vikrant Dewangan +1

Traditional greedy tokenization methods have been a critical step in Natural Language Processing (NLP), influencing how text is converted into tokens and directly impacting model p…

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…