24 citations · 42 across the 14 of their papers we have counts for
14 papers
Detecting Functional Memorization in Code Language Models
Matthieu Meeus, Anil Ramakrishna, Shengyuan Hu +3
Large language models (LLMs) are increasingly used to generate code at scale. Meanwhile, prior work has investigated whether training data may be recoverable from model outputs, by…
RAT-Bench: A Comprehensive Benchmark for Text Anonymization
Nataša Krčo, Zexi Yao, Matthieu Meeus +1
Data containing personal information is increasingly used to train, fine-tune, or query Large Language Models (LLMs). Text is typically scrubbed of identifying information prior to…
Counterfactual Influence as a Distributional Quantity
Matthieu Meeus, Igor Shilov, Georgios Kaissis +1
Machine learning models are known to memorize samples from their training data, raising concerns around privacy and generalization. Counterfactual self-influence is a popular metri…
Exploring the limits of strong membership inference attacks on large language models
Jamie Hayes, Ilia Shumailov, Christopher A. Choquette-Choo +13
State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language mode…
Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal
Xiaoxue Yang, Bozhidar Stevanoski, Matthieu Meeus +1
Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted external content. This makes them a pri…
The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
Matthieu Meeus, Lukas Wutschitz, Santiago Zanella-Béguelin +2
How much information about training samples can be leaked through synthetic data generated by Large Language Models (LLMs)? Overlooking the subtleties of information flow in synthe…
ChocoLlama: Lessons Learned From Teaching Llamas Dutch
Matthieu Meeus, Anthony Rathé, François Remy +3
While Large Language Models (LLMs) have shown remarkable capabilities in natural language understanding and generation, their performance often lags in lower-resource, non-English…
SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)
Matthieu Meeus, Igor Shilov, Shubham Jain +3
Whether LLMs memorize their training data and what this means, from measuring privacy leakage to detecting copyright violations, has become a rapidly growing area of research. In t…
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…
Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Models
Nataša Krčo, Florent Guépin, Matthieu Meeus +2
Synthetic data generators and machine learning models can memorize their training data, posing privacy concerns. Membership inference attacks (MIAs) are a standard method of estima…
Copyright Traps for Large Language Models
Matthieu Meeus, Igor Shilov, Manuel Faysse +1
Questions of fair use of copyright-protected content to train Large Language Models (LLMs) are being actively debated. Document-level inference has been proposed as a new task: inf…
Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models
Matthieu Meeus, Shubham Jain, Marek Rei +1
With large language models (LLMs) poised to become embedded in our daily lives, questions are starting to be raised about the data they learned from. These questions range from pot…
Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data
Florent Guépin, Matthieu Meeus, Ana-Maria Cretu +1
Synthetic data is emerging as one of the most promising solutions to share individual-level data while safeguarding privacy. While membership inference attacks (MIAs), based on sha…
Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing
Matthieu Meeus, Florent Guépin, Ana-Maria Cretu +1
Synthetic data is seen as the most promising solution to share individual-level data while preserving privacy. Shadow modeling-based Membership Inference Attacks (MIAs) have become…