ICML-Learning to Generate Noise for Multi-Attack Robustness

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

Learning to Generate Noise for Multi-Attack Robustness

                 Divyam Madaan 1 Jinwoo Shin 2 3 Sung Ju Hwang 1 3 4

             Abstract                as accurate, since incorrect predictions may lead to severe
    Adversarial learning has emerged as one of the       consequences. Notably, it is well-known that the existing
    successful techniques to circumvent the suscep-      neural networks are highly susceptible to adversarial ex-
    tibility of existing methods against advers ...

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：Robustness generate Learning earning Attack