| Oct 19, 2026 | [Preprint]: We released our latest preprint, Reliable Estimation of Differential Privacy under Selection Bias, on arXiv! In this work, we identify and fix a selection bias found in standard privacy auditing protocols. Read the full paper here! 📄 |
| Oct 16, 2026 | [Preprint]: Our new preprint, Detectability without Interference: Efficient Canary Design for Privacy Auditing in One Run, is live on arXiv. It frames canary optimization as a bi-level problem and introduces IBIS, a framework that efficiently crafts multiple canaries for privacy audits in one run. You can check it out here!📄 |
| Oct 09, 2026 | [Paper]: Our paper, Assessing Per-Sample Membership Inference Vulnerability without Retraining, has been accepted at NeurIPS 2026. It’s available here. See you in Paris! 🎉 |
| Jun 01, 2026 | [Visit]: I am joining the Vector Institute in Toronto as a Visiting PhD Student with Nicolas Papernot in the Clever Hans Lab.  |
| May 15, 2026 | [Preprint]: Our new preprint, Assessing Per-Sample Membership Inference Vulnerability without Retraining, is now live on arXiv. The paper presents an efficient approach to evaluate per-sample membership inference attack (MIA) vulnerability while bypassing the overhead of retraining shadow models. Check it out here.📄 |
| Oct 01, 2025 | [PhD] I started my PhD in the DATA Team at ENS-PSL, working on Differential Privacy and Membership Inference Attacks, under the supervision of Olivier Cappé and Jamal Atif.  |