3 papers
cs.CL2025
The Mosaic Memory of Large Language Models
Igor Shilov, Matthieu Meeus, Yves-Alexandre de Montjoye
As Large Language Models (LLMs) become widely adopted, understanding how they learn from, and memorize, training data becomes crucial. Memorization in LLMs is widely assumed to onl…
cs.CR2024
QueryCheetah: Fast Automated Discovery of Attribute Inference Attacks Against Query-Based Systems
Bozhidar Stevanoski, Ana-Maria Cretu, Yves-Alexandre de Montjoye
Query-based systems (QBSs) are one of the key approaches for sharing data. QBSs allow analysts to request aggregate information from a private protected dataset. Attacks are a cruc…
cs.LG2024
Correlation inference attacks against machine learning models
Ana-Maria Creţu, Florent Guépin, Yves-Alexandre de Montjoye
Despite machine learning models being widely used today, the relationship between a model and its training dataset is not well understood. We explore correlation inference attacks,…