zoukankan      html  css  js  c++  java
  • Paper Reading——LEMNA:Explaining Deep Learning based Security Applications

    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.  

  • 相关阅读:
    问答
    正在设计taijilang的解析器,真可谓尸横遍地
    因为这些理由而坚持用grunt?其实它们都不成立。
    开始设计taijijs
    从grunt转到gulp
    google 索引
    :: operator
    用coffeescript写构造函数
    jade与angular.js
    angular.js 资料收集
  • 原文地址:https://www.cnblogs.com/xlwang1995/p/10056309.html
Copyright © 2011-2022 走看看