3.7k citations · 12.4k across the 59 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2022★ 46 cited
Deduplicating Training Data Mitigates Privacy Risks in Language Models
Nikhil Kandpal, Eric Wallace, Colin Raffel
Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorize…
cs.CR2020★ 273 cited
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…