Matthieu Meeus

Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses

Unique between the lines: benchmarking re-identification risk for text anonymization

Exploring the limits of strong membership inference attacks on large language models

The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text

The Canary’s Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text

Lost in the Averages: Evaluating record-specific MIAs against Machine Learning models