Paper Reading——LEMNA:Explaining Deep Learning based Security Applications

概述Motivation: The lack of transparency of the deep  learning models creates key barriers to establishing trusts to the model or effectively troubleshooting classification errors Common methods on non-se

Motivation:

The lack of transparency of the deep  learning models creates key barrIErs to establishing trusts to the model or effectively troubleshooting classification errors

Common methods on non-security applications:

forward propagation / back propagation / under a blackBox setting 

the basic IDea is to approximate the local decision boundary using a linear model to infer the important features.

Insights:

A mixture regression model : can approximate both linear and non-linear decision boundarIEs 

Fused Lasso: a panalty term commonly used for capturing frature dependency.

By adding fused lasso to the learning process,the mixture regression model can take features as a group and thus capture the dependency between adjacent features.

Evaluations:

classifying pdf malware: trained on 10000 pdf files 

detecting the function start to reverse-engineer  binary code. 

Innovation:

Under a  black-Box setting :

Give an input data instance x and a classifIEr such as an RNN,  IDentify a small set of features that have key contributions to the classification of x.  

总结

以上是内存溢出为你收集整理的Paper Reading——LEMNA:Explaining Deep Learning based Security Applications全部内容，希望文章能够帮你解决Paper Reading——LEMNA:Explaining Deep Learning based Security Applications所遇到的程序开发问题。

如果觉得内存溢出网站内容还不错，欢迎将内存溢出网站推荐给程序员好友。