Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Nolkha, Vidita"'
Autor:
Negoescu, Diana M., Gonzalez, Humberto, Orjany, Saad Eddin Al, Yang, Jilei, Lut, Yuliia, Tandra, Rahul, Zhang, Xiaowen, Zheng, Xinyi, Douglas, Zach, Nolkha, Vidita, Ahammad, Parvez, Samorodnitsky, Gennady
We introduce Epsilon*, a new privacy metric for measuring the privacy risk of a single model instance prior to, during, or after deployment of privacy mitigation strategies. The metric requires only black-box access to model predictions, does not req
Externí odkaz:
http://arxiv.org/abs/2307.11280