ICML-Label Inference Attacks from Log-loss Scores

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Label Inference Attacks from Log-loss Scores

Abhinav Aggarwal 1 Shiva Prasad Kasiviswanathan 1 Zekun Xu 1 Oluwaseyi Feyisetan 1 Nathanael Teissier 1
                                     PN
             Abstract                  that i=1 ui,k = 1. Let 2 [K]N be a labeling. Then, the
   Log-loss (also known as cross-entropy loss) met-        K-ary log-loss (or, cross-entropy loss) on u with respect to
   ric is ubiquitously used across machine learning         , denoted by LL OSS (u; ), is defin ...

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Inference erence Attack scores label