Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice. Cooper, A. F., Choquette-Choo, C. A., Bogen, M., Jagielski, M., Filippova, K., Liu, K. Z., Chouldechova, A., Hayes, J., Huang, Y., Mireshghallah, N., Shumailov, I., Triantafillou, E., Kairouz, P., Mitchell, N., Liang, P., Ho, D. E., Choi, Y., Koyejo, S., Delgado, F. A., Grimmelmann, J., Shmatikov, V., Sa, C. D., Barocas, S., Cyphert, A., Lemley, M. A., danah boyd , Vaughan, J. W., Brundage, M., Bau, D., Neel, S., Jacobs, A. Z., Terzis, A., Wallach, H. M., Papernot, N., & Lee, K. CoRR, 2024.
Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice [link]Paper  doi  bibtex   
@article{DBLP:journals/corr/abs-2412-06966,
  author       = {A. Feder Cooper and
                  Christopher A. Choquette{-}Choo and
                  Miranda Bogen and
                  Matthew Jagielski and
                  Katja Filippova and
                  Ken Ziyu Liu and
                  Alexandra Chouldechova and
                  Jamie Hayes and
                  Yangsibo Huang and
                  Niloofar Mireshghallah and
                  Ilia Shumailov and
                  Eleni Triantafillou and
                  Peter Kairouz and
                  Nicole Mitchell and
                  Percy Liang and
                  Daniel E. Ho and
                  Yejin Choi and
                  Sanmi Koyejo and
                  Fernando A. Delgado and
                  James Grimmelmann and
                  Vitaly Shmatikov and
                  Christopher De Sa and
                  Solon Barocas and
                  Amy Cyphert and
                  Mark A. Lemley and
                  danah boyd and
                  Jennifer Wortman Vaughan and
                  Miles Brundage and
                  David Bau and
                  Seth Neel and
                  Abigail Z. Jacobs and
                  Andreas Terzis and
                  Hanna M. Wallach and
                  Nicolas Papernot and
                  Katherine Lee},
  title        = {Machine Unlearning Doesn't Do What You Think: Lessons for Generative
                  {AI} Policy, Research, and Practice},
  journal      = {CoRR},
  volume       = {abs/2412.06966},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2412.06966},
  doi          = {10.48550/ARXIV.2412.06966},
  eprinttype    = {arXiv},
  eprint       = {2412.06966},
  timestamp    = {Wed, 25 Jun 2025 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2412-06966.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 0