USENIX supports diversity, equity, and inclusion and condemns hate and discrimination.
Extracting Training Data from Large Language Models
Submitted by jasmine@usenix.org on June 14, 2021 - 2:30 pm
| Title | Extracting Training Data from Large Language Models |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Carlini N, Tramèr F, Wallace E, Jagielski M, Herbert-Voss A, Lee K, Roberts A, Brown T, Song D, Erlingsson Ú, Oprea A, Raffel C |
| Conference Name | 30th USENIX Security Symposium (USENIX Security 21) |
| Date Published | 08/2021 |
| Publisher | USENIX Association |
| ISBN Number | 978-1-939133-24-3 |
| URL | https://www.usenix.org/conference/usenixsecurity21/presentation/carlini-extracting |
- DBLP
- Log in or Register to post comments
- Google Scholar
- BibTeX