MoPe: Model Perturbation based Privacy Attacks on Language Models. Li, M., Wang, J., Wang, J. G., & Neel, S. In Bouamor, H., Pino, J., & Bali, K., editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 13647–13660, 2023. Association for Computational Linguistics.
MoPe: Model Perturbation based Privacy Attacks on Language Models [link]Paper  doi  bibtex   
@inproceedings{DBLP:conf/emnlp/LiWWN23,
  author       = {Marvin Li and
                  Jason Wang and
                  Jeffrey G. Wang and
                  Seth Neel},
  editor       = {Houda Bouamor and
                  Juan Pino and
                  Kalika Bali},
  title        = {MoPe: Model Perturbation based Privacy Attacks on Language Models},
  booktitle    = {Proceedings of the 2023 Conference on Empirical Methods in Natural
                  Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},
  pages        = {13647--13660},
  publisher    = {Association for Computational Linguistics},
  year         = {2023},
  url          = {https://doi.org/10.18653/v1/2023.emnlp-main.842},
  doi          = {10.18653/V1/2023.EMNLP-MAIN.842},
  timestamp    = {Fri, 12 Apr 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/emnlp/LiWWN23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 0