Matthieu Meeus

Email: mm422@ic.ac.uk

Matthieu joined the Computational Privacy Group as a PhD student in Oct 2022. His research interests include privacy attacks against computer vision and language models and bias and fairness in machine learning.

Originally from Belgium, Matthieu obtained his BSc from KU Leuven in Mechanical Engineering. Afterwards he pursued a MEng in Energy Technology at the University of California, Berkeley, where he worked on projects related to vertical axis wind turbines and EV charging strategies. While staying in the Bay Area, he acquired a strong interest in data science.

Hence, he pursued an MSc in Computational Science and Engineering at Harvard University, where he studied core data science and computational software development. He assisted in research working on solving PDEs with neural networks and spent a summer as Energy Optimization Intern at Tesla in Palo Alto, working on smart charge/discharge strategies for residential batteries.

Before joining the CPG, he worked as data scientist for McKinsey and Company in NYC, as part of the internal research team People Analytics and Measurement. His work included predictive modeling using mainly internal data from the company, as well as developing NLP solutions.


News


Publications

  • Meeus, M., Jain, S., Rei, M. and de Montjoye Y. A. Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models. 33rd USENIX Security Symposium (USENIX Security 2024) (2024).
    Selected Press: Le Monde
  • Meeus, M., Shilov, I., Faysse, M. and de Montjoye Y. A. Copyright Traps for Large Language Models. 41st International Conference on Machine Learning (ICML 2024) (2024).
    Selected Press: MIT Technology Review, Nature News
  • Guépin, F., Krčo, N., Meeus, M. and de Montjoye Y. A. Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Models. ArXiv preprint (2024).
  • Meeus, M., Shilov, I., and de Montjoye Y. A. Mosaic Memory: Fuzzy Duplication in Copyright Traps for Large Language Models. ArXiv preprint (2024).
  • Guépin, F., Meeus, M., Cretu, A.-M., and de Montjoye Y. A. Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data. 18th DPM International Workshop on Data Privacy Management, Sept 2023, The Hague (2023).
  • Meeus, M., Guépin, F., Cretu, A.-M., and de Montjoye Y. A. Achilles’ Heels: Vulnerable Record Identification in Synthetic Data Publishing. 28th European Symposium on Research in Computer Security (ESORICS), Sept 2023, The Hague (2023).
  • Meeus, M., Jain, S., and de Montjoye Y. A. Concerns about using a digital mask to safeguard patient privacy. Matters Arising in Nature Medicine, July 2023 (2023).