P. Kairouz

Most-cited papers

1. Primary sequence of Xenopus laevis Na+-K+-ATPase and its localization in A6 kidney cells.

   François Verrey, P. Kairouz, Esther Schaerer, P. Fuentes +3 more

   1989American Journal of Physiology59 citations

   Semantic Scholar

   Save

2. Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice

   A. Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Matthew Jagielski +31 more

   2024arXiv.org49 citations

   Semantic Scholar

   Save

3. Language Models May Verbatim Complete Text They Were Not Explicitly Trained On

   Ken Liu, Christopher A. Choquette-Choo, Matthew Jagielski, P. Kairouz +3 more

   2025International Conference on Machine Learning32 citations

   Semantic Scholar

   Save

4. Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

   A. Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Kevin Klyman +33 more

   2024Neural Information Processing Systems19 citations Open access

   Semantic Scholar

   Save

5. Can Large Language Models Really Recognize Your Name?

   Dzung Pham, P. Kairouz, Niloofar Mireshghallah, Eugene Bagdasarian +2 more

   2025Conference on Fairness, Accountability and Transparency10 citations Open access

   Semantic Scholar

   Save

6. Evaluation for the NeurIPS Machine Unlearning Competition

   Eleni Triantafillou, P. Kairouz

   10 citations

   Semantic Scholar

   Save

7. Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data

   Stefan Schoepf, M. Mozer, N. Mitchell, A. Brintrup +3 more

   2025arXiv.org7 citations

   Semantic Scholar

   Save

8. MAPLE: Metadata Augmented Private Language Evolution

   Eli Chien, Yu-Zheng Hu, Ryan McKenna, Shanshan Wu +2 more

   2026arXiv.org5 citations

   Semantic Scholar

   Save

9. Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment

   Yavuz Faruk Bakman, D. Yaldiz, Eleni Triantafillou, P. Kairouz +2 more

   2026Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026)4 citations

   Semantic Scholar

   Save

10. Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography

    Ilia Shumailov, Daniel Ramage, Sarah Meiklejohn, P. Kairouz +3 more

    2025arXiv.org4 citations

    Semantic Scholar

    Save

11. A Technical Policy Blueprint for Trustworthy Decentralized AI

    Hasan Kassem, Orion Banks, O. Benjelloun, S. Cansiz +19 more

    2025arXiv.org2 citations

    Semantic Scholar

    Save

12. Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning

    Chao-Ran Chen, Dayu Yuan, P. Kairouz

    2026arXiv.org0 citations

    Semantic Scholar

    Save

13. Examining Data Compartmentalization for AI Governance

    N. Mitchell, P. Kairouz, Eleni Triantafillou

    0 citations

    Semantic Scholar

    Save