MoPe: Model Perturbation-based Privacy Attacks on Language Models. Li, M., Wang, J., Wang, J. G., & Neel, S. CoRR, 2023.
MoPe: Model Perturbation-based Privacy Attacks on Language Models [link]Paper  doi  bibtex   
@article{DBLP:journals/corr/abs-2310-14369,
  author       = {Marvin Li and
                  Jason Wang and
                  Jeffrey G. Wang and
                  Seth Neel},
  title        = {MoPe: Model Perturbation-based Privacy Attacks on Language Models},
  journal      = {CoRR},
  volume       = {abs/2310.14369},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2310.14369},
  doi          = {10.48550/ARXIV.2310.14369},
  eprinttype    = {arXiv},
  eprint       = {2310.14369},
  timestamp    = {Mon, 25 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2310-14369.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 0