ML Anthology

Abascal, John

2 publications

ICLR 2026 Black-Box Privacy Attacks on Shared Representations in Multitask Learning John Abascal, Nicolás Berrios, Alina Oprea, Jonathan Ullman, Adam Smith, Matthew Jagielski
ICMLW 2023 TMI! Finetuned Models Spill Secrets from Pretraining John Abascal, Stanley Wu, Alina Oprea, Jonathan Ullman