Publications

Recent publications from members of the research team are listed below. Luc Rocher’s full list of publications is available on Google Scholar.

Publications and preprints

Jessica Morley, Luc Rocher, 2024. Building infrastructure is key to unifying UK health data. BMJ, 387.

Franziska Sofia Hafner, and Luc Rocher, 2024. Gender Trouble in Language Models: A Critical Audit Guided by Gender Performativity Theory. Zenodo.

Andrea Gadotti, Luc Rocher, Florimond Houssiau., Ana-Maria Creţu and Yves-Alexandre de Montjoye, 2024. Anonymization: The imperfect science of using data while preserving privacy. Science Advances, 10(29), p.eadn7053.

Meenatchi Sundaram Mutu Selva Annamalai, Andrea Gadotti and Luc Rocher, 2024. A linear reconstruction approach for attribute inference attacks against synthetic data. In 33rd USENIX Security Symposium.

Ibrahim, L., Luc Rocher and Valdivia, A., 2024. Characterizing and modeling harms from interactions with design patterns in AI interfaces. arXiv preprint arXiv:2404.11370.

Adriano Belisario, Scott Hale and Luc Rocher, 2024. Into the crossfire: evaluating the use of a language model to crowdsource gun violence reports. arXiv preprint arXiv:2401.12989.

Luc Rocher, Arnaud J. Tournier and Yves-Alexandre de Montjoye, 2023. Adversarial competition and collusion in algorithmic markets. Nature Machine Intelligence, 5(5), pp.497-504.

Florimond Houssiau., Luc Rocher and Yves-Alexandre de Montjoye, 2022. On the difficulty of achieving Differential Privacy in practice: user-level guarantees in aggregate location data. Nature communications, 13(1), p.29.

Luc Rocher, Meenatchi Sundaram Mutu Selva Annamalai and Yves-Alexandre de Montjoye, 2021. The Observatory of Anonymity: An interactive tool to understand re-identification risks in 89 countries. In Companion Proceedings of the Web Conference 2021.

Luc Rocher, Julien M. Hendrickx and Yves-Alexandre de Montjoye, 2019. Estimating the success of re-identifications in incomplete datasets using generative models. Nature communications, 10(1), pp.1-9.

Andrea Gadotti, Florimond Houssiau., Luc Rocher, Ben Livshits and Yves-Alexandre de Montjoye, 2019. When the signal is in the noise: Exploiting diffix’s sticky noise. In 28th USENIX Security Symposium.