activity
20242026
collaborators

6 papers

stat.ML2026

Assessing Per-Sample Membership Inference Vulnerability without Retraining

Valentin Dorseuil, Jamal Atif, Olivier Cappé

Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by t…

cs.LG2026

Certified Per-Instance Unlearning Using Individual Sensitivity Bounds

Hanna Benarroch, Jamal Atif, Olivier Cappé

Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case sensitivity. Such conservative…

cs.LG2025

On the MIA Vulnerability Gap Between Private GANs and Diffusion Models

Ilana Sebag, Jean-Yves Franceschi, Alain Rakotomamonjy +2

Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis. While both can be trained under differential privac…

cs.CL2025

Memorization in Fine-Tuned Large Language Models

Danil Savine

This study investigates the mechanisms and factors influencing memorization in fine-tuned large language models (LLMs), with a focus on the medical domain due to its privacy-sensit…

stat.ML2025

Differentially Private Gradient Flow based on the Sliced Wasserstein Distance

Ilana Sebag, Muni Sreenivas Pydi, Jean-Yves Franceschi +4

Safeguarding privacy in sensitive training data is paramount, particularly in the context of generative modeling. This can be achieved through either differentially private stochas…

cs.LG2024

Optimal Classification under Performative Distribution Shift

Edwige Cyffers, Muni Sreenivas Pydi, Jamal Atif +1

Performative learning addresses the increasingly pervasive situations in which algorithmic decisions may induce changes in the data distribution as a consequence of their public de…