Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Anchored or Drifting: What Recursive Self-Generation Reveals About Training Data
Wojciech Łapacz, Stanisław Pawlak
Large generative models are known to memorize their training data, posing severe privacy risks. Yet, current methods to detect training membership typically rely on the weak signal…
cs.LG2026
Dataset Usage Inference without Shadow Models or Held-out Data
Wojciech Łapacz, Stanisław Pawlak, Jan Dubiński +2
How much of my data was used to train a machine learning model? Dataset Usage Inference (DUI) aims to answer this by estimating what fraction of a dataset contributed to a model's…