73 citations · 585 across the 58 of their papers we have counts for
17 papers · 1 filter
Lower Bounds for Public-Private Learning under Distribution Shift
Amrith Setlur, Pratiksha Thaker, Jonathan Ullman
The most effective differentially private machine learning algorithms in practice rely on an additional source of purportedly public data. This paradigm is most interesting when th…
TMI! Finetuned Models Leak Private Information from their Pretraining Data
John Abascal, Stanley Wu, Alina Oprea +1
Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned…
From Robustness to Privacy and Back
Hilal Asi, Jonathan Ullman, Lydia Zakynthinou
We study the relationship between two desiderata of algorithms in statistical inference and machine learning: differential privacy and robustness to adversarial data corruptions. T…
Multitask Learning via Shared Features: Algorithms and Hardness
Konstantina Bairaktari, Guy Blanc, Li-Yang Tan +2
We investigate the computational efficiency of multitask learning of Boolean functions over the -dimensional hypercube, that are related by means of a feature representation of…
SNAP: Efficient Extraction of Private Properties with Poisoning
Harsh Chaudhari, John Abascal, Alina Oprea +3
Property inference attacks allow an adversary to extract global properties of the training dataset from a machine learning model. Such attacks have privacy implications for data ow…
How to Combine Membership-Inference Attacks on Multiple Updated Models
Matthew Jagielski, Stanley Wu, Alina Oprea +2
A large body of research has shown that machine learning models are vulnerable to membership inference (MI) attacks that violate the privacy of the participants in the training dat…