Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data
Kareem Amin, Rudrajit Das, Alessandro Epasto +4
The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets. Ho…
cs.LG2026
Is your algorithm unlearning or untraining?
Eleni Triantafillou, Ahmed Imtiaz Humayun, Monica Ribero +3
As models are getting larger and are trained on increasing amounts of data, there has been an explosion of interest into how we can ``delete'' specific data points or behaviours fr…
stat.ML2026
Regularized -Divergence Kernel Tests
Mónica Ribero, Antonin Schrab, Arthur Gretton
We propose a framework to construct practical kernel-based two-sample tests from the family of -divergences. The test statistic is computed from the witness function of a regula…