[论文]Detecting Adversarial Exampl

2020-03-18  本文已影响0人  wangxiaoguang

论文题目:Detecting Adversarial Examples Using Data Manifolds
论文地址:http://susmitjha.github.io/papers/milcom18.pdf
**DOI: **10.1109/MILCOM.2018.8599691

Our approach is based on identifying a low dimensional manifold in which the training samples lie, and then using the distance of a new observation from this manifold to identify whether this data point is adversarial or not.

上一篇下一篇

猜你喜欢

热点阅读