MoPe: Model Perturbation based Privacy Attacks on Language Models

MoPe: Model Perturbation based Privacy Attacks on Language Models Marvin Li author Jason Wang author Jeffrey Wang author Seth Neel author 2023-12 text Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing Houda Bouamor editor Juan Pino editor Kalika Bali editor Association for Computational Linguistics Singapore conference publication li-etal-2023-mope 10.18653/v1/2023.emnlp-main.842 https://aclanthology.org/2023.emnlp-main.842/ 2023-12 13647 13660