activity
20242026
most citedMembership Inference Attacks Cannot Prove that a Model Was Trained On Your Data

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing 2024Show all

2 papers · 1 filter

cs.LG2024★ 1 cited

Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data

Jie Zhang, Debeshee Das, Gautam Kamath +1

We consider the problem of a training data proof, where a data creator or owner wants to demonstrate to a third party that some machine learning model was trained on their data. Tr…

cs.CR2024

Blind Baselines Beat Membership Inference Attacks for Foundation Models

Debeshee Das, Jie Zhang, Florian Tramèr

Membership inference (MI) attacks try to determine if a data sample was used to train a machine learning model. For foundation models trained on unknown Web data, MI attacks are of…