activity
20182023
most citedScalable Extraction of Training Data from (Production) Language Models

83 citations · 181 across the 5 of their papers we have counts for

collaborators

10 papers

cs.LG202383 cited

Scalable Extraction of Training Data from (Production) Language Models

Milad Nasr, Nicholas Carlini, Jonathan Hayase +7

This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training da…

cs.LG20225 cited

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…

cs.LG202211 cited

Subverting Fair Image Search with Generative Adversarial Perturbations

Avijit Ghosh, Matthew Jagielski, Christo Wilson

In this work we explore the intersection fairness and robustness in the context of ranking: when a ranking model has been calibrated to achieve some definition of fairness, is it p…

cs.LG20229 cited

Debugging Differential Privacy: A Case Study for Privacy Auditing

Florian Tramer, Andreas Terzis, Thomas Steinke +3

Differential Privacy can provide provable privacy guarantees for training data in machine learning. However, the presence of proofs does not preclude the presence of errors. Inspir…

cs.CR2020

Extracting Training Data from Large Language Models

Nicholas Carlini, Florian Tramer, Eric Wallace +9

It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary ca…

cs.CR202073 cited

Auditing Differentially Private Machine Learning: How Private is Private SGD?

Matthew Jagielski, Jonathan Ullman, Alina Oprea

We investigate whether Differentially Private SGD offers better privacy in practice than what is guaranteed by its state-of-the-art analysis. We do so via novel data poisoning atta…