4 papers
Learning To Sample From Diffusion Models Via Inverse Reinforcement Learning
Constant Bourdrez, Alexandre Vérine, Olivier Cappé
Diffusion models generate samples through an iterative denoising process guided by a pretrained neural network. Once the denoiser is fixed, the sampling algorithm itself (noise sch…
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…
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…
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…