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:
    jQuery 从无到有.一天完成.
    JavaScript从无到有(一天完成)
    HTML(第一篇)
    前端认识
    三元表达式,列表推导是,字典生成式
    ORM之youku项目小练习(上)
    高逼格壁纸
    pymysql 基操全套
    怎么学好编程?
    mysql 事务
  • 原文地址:https://www.cnblogs.com/xlwang1995/p/10056309.html
Copyright © 2011-2022 走看看