5 papers
Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
Sayan Biswas, Antoine Boutet, Davide Frey +7
Decentralized learning (DL) is an emerging machine learning paradigm where nodes collaboratively train models without a central server. However, the collaborative nature of DL make…
Towards the Anonymization of the Language Modeling
Antoine Boutet, Lucas Magnana, Juliette Sénéchal
Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant privacy concerns, especially wh…
Leverage Unlearning to Sanitize LLMs
Antoine Boutet, Lucas Magnana
Pre-trained large language models (LLMs) are becoming useful for various tasks. To improve their performance on certain tasks, it is necessary to fine-tune them on specific data co…
The Model's Language Matters: A Comparative Privacy Analysis of LLMs
Abhishek K. Mishra, Antoine Boutet, Lucas Magnana
Large Language Models (LLMs) are increasingly deployed across multilingual applications that handle sensitive data, yet their scale and linguistic variability introduce major priva…
"I'm not for sale" -- Perceptions and limited awareness of privacy risks by digital natives about location data
Antoine Boutet, Victor Morel
Although mobile devices benefit users in their daily lives in numerous ways, they also raise several privacy concerns. For instance, they can reveal sensitive information that can…