Title: Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
Award ID(s):
2302968 2124104 2125530
PAR ID:
10639503
Author(s) / Creator(s):
; ;
Publisher / Repository:
Association for Computational Linguistics
Date Published:
Page Range / eLocation ID:
22872 to 22888
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this