Publications

Publications & preprints

Peer reviewed research and preprints, newest first. Ongoing projects appear on the research page.

2026

Efficient Provably Private Classification with a Tabular Foundation Model

Talal Alrawajfeh, Cristiana Diaconu, Ossi Räisä, Sebastian Rodriguez Beltran, Yuan He, John Bronskill, Richard E. Turner, Antti Honkela

arXiv preprint, arXiv:2610.10068. 2026.

BibTeX
@misc{alrawajfeh2026privtab,
  title = {Efficient Provably Private Classification with a Tabular Foundation Model},
  author = {Alrawajfeh, Talal and Diaconu, Cristiana and Räisä, Ossi and Rodriguez Beltran, Sebastian and He, Yuan and Bronskill, John and Turner, Richard E. and Honkela, Antti},
  year = {2026},
  eprint = {2610.10068},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2610.10068}
}

Privacy Leakage via Output Label Space and Differentially Private Continual Learning

Marlon Tobaben, Talal Alrawajfeh, Marcus Klasson, Mikko A. Heikkilä, Arno Solin, Antti Honkela

Transactions on Machine Learning Research. 2026.

Marlon Tobaben and Talal Alrawajfeh contributed equally.

BibTeX
@article{tobaben2026privacy,
  title = {Privacy Leakage via Output Label Space and Differentially Private Continual Learning},
  author = {Tobaben, Marlon and Alrawajfeh, Talal and Klasson, Marcus and Heikkilä, Mikko A. and Solin, Arno and Honkela, Antti},
  journal = {Transactions on Machine Learning Research},
  year = {2026},
  url = {https://openreview.net/forum?id=ejnVWfknCm}
}

2025

Noise-Aware Differentially Private Variational Inference

Talal Alrawajfeh, Joonas Jälkö, Antti Honkela

Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 258:4987–4995. 2025.

BibTeX
@InProceedings{pmlr-v258-alrawajfeh25a,
  title = {Noise-Aware Differentially Private Variational Inference},
  author = {Alrawajfeh, Talal and Jälkö, Joonas and Honkela, Antti},
  booktitle = {Proceedings of the 28th International Conference on Artificial Intelligence and Statistics},
  pages = {4987--4995},
  year = {2025},
  volume = {258},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v258/alrawajfeh25a.html}
}