Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy

Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy Daphne Ippolito author Florian Tramer author Milad Nasr author Chiyuan Zhang author Matthew Jagielski author Katherine Lee author Christopher Choquette Choo author Nicholas Carlini author 2023-09 text Proceedings of the 16th International Natural Language Generation Conference C Maria Keet editor Hung-Yi Lee editor Sina Zarrieß editor Association for Computational Linguistics Prague, Czechia conference publication ippolito-etal-2023-preventing 10.18653/v1/2023.inlg-main.3 https://aclanthology.org/2023.inlg-main.3/ 2023-09 28 53