Papernot N, Mcdaniel P, Goodfellow I, et al. Practical Black-Box Attacks against Machine Learning[C]. computer and communications security, 2017: 506-519.

@article{papernot2017practical,

title={Practical Black-Box Attacks against Machine Learning},

author={Papernot, Nicolas and Mcdaniel, Patrick and Goodfellow, Ian and Jha, Somesh and Celik, Z Berkay and Swami, Ananthram},

pages={506--519},

year={2017}}

Adversarial samples 构造策略中的black-box策略. black-box attacks, 即不依赖所针对的神经网络\(O\)的参数(像FGSM需要关于样本求导), 不依赖训练\(O\)所需的样本.

主要内容

算法为:

策略如下, 我们现在仅有一个黑盒般的神经网络\(O\), 我们喂入一个样本\(x\)就会有一个输出, 记\(\tilde{O}(x)\)为对应的预测的类, 即

\[\tilde{O}(x) = \arg \max_{j \in 0, \ldots, N} O_j(x),
\]

其中\(O_j(x)\)是概率向量\(O(x)\)的第\(j\)个元素.

我们构造一个新的神经网络\(S\), 以期望训练\(S\)使得\(S\)和\(O\)二者的分类边界近似. 因为没有训练样本, 一种想法是人工生成训练样本(随机生成是可以预料到的方法, 但是这种方法作者说不好).

Jacobian-based Dataset Augmentation

假设有一批最开始的样本(可以是找的少量训练样本, 或者随机生成的样本), 设为\(S_0\), 将这批样本畏入\(O\)获得对应的样本标签(虽然可能是误判, 我们的目的是拟合\(O\)),

\[D \leftarrow \{(x, \tilde{O}(x)):x \in S_0\},
\]

再将这批数据喂入\(S\)训练\(S\), 现在我们需要更新\(S_0\):

\[S_1 \leftarrow \{x + \lambda \cdot \mathrm{sgn} (J_F[\tilde{O}(x)]: x \in S_0]\} \cup S_0.
\]

其中\(J_F[\tilde{O}(x)]\)表示\(\tilde{O}(x)\)关于\(x\)的导数(这个idea应该是中FGSM中来的, 比较Goodfellow是联合作者).

后续的数据的更新是类似的.

现在假设我们已经训练好了\(S\), 我们需要在\(S\)的基础上构造adversarial samples, 这些作者直接借鉴了部分关于white-box的工作(FGSM等), 我们只需利用white-box attacks 去欺骗\(S\)即可.

Note

  • 网络结构, 比如网络的层数, 训练时的epoch等等对结果的影响有限.
  • white-box 方法选择对结果的影响有限.
  • 该方法可以扩展到除DNN以外的机器学习上, 比如逻辑斯蒂回归(决策树似乎也可, 但是没找到怎么实现的方案).
  • 为了提高网络的稳定性, 我们可以在训练的时候加入adversarial samples, 但是作者发现, 最好是在\(\epsilon\)(输入摄动)较大但有限的adversarial samples 上训练比较好.

Practical Black-Box Attacks against Machine Learning的更多相关文章

  1. (转)Is attacking machine learning easier than defending it?

    转自:http://www.cleverhans.io/security/privacy/ml/2017/02/15/why-attacking-machine-learning-is-easier- ...

  2. Federated Machine Learning: Concept and Applications

    郑重声明:原文参见标题,如有侵权,请联系作者,将会撤销发布! Qiang Yang, Yang Liu, Tianjian Chen, and Yongxin Tong. 2019. Federate ...

  3. Practical Machine Learning For The Uninitiated

    Practical Machine Learning For The Uninitiated Last fall when I took on ShippingEasy's machine learn ...

  4. Lessons learned developing a practical large scale machine learning system

    原文:http://googleresearch.blogspot.jp/2010/04/lessons-learned-developing-practical.html Lessons learn ...

  5. How do I learn machine learning?

    https://www.quora.com/How-do-I-learn-machine-learning-1?redirected_qid=6578644   How Can I Learn X? ...

  6. How do I learn mathematics for machine learning?

    https://www.quora.com/How-do-I-learn-mathematics-for-machine-learning   How do I learn mathematics f ...

  7. [C5] Andrew Ng - Structuring Machine Learning Projects

    About this Course You will learn how to build a successful machine learning project. If you aspire t ...

  8. [C2P1] Andrew Ng - Machine Learning

    About this Course Machine learning is the science of getting computers to act without being explicit ...

  9. [C2P2] Andrew Ng - Machine Learning

    ##Linear Regression with One Variable Linear regression predicts a real-valued output based on an in ...

随机推荐

  1. The Go tools for Windows + Assembler很好玩

    我想用python做个tiny BASIC编译器.赋值和加减乘除,IF和FOR. 语法分析python有ply包,用ply.lex和ply.yacc做个计算器很简单,我已经做了. 做个解释器应该也不难 ...

  2. Portrait Photography Beginners Guide

    Please visit photoandtips稻糠亩 for more information. 六级/考研单词: vogue, derive, gorgeous, thereby, strict ...

  3. 12. Fedora 中文乱码问题

    1. Rhythmbox(音乐播放器乱码) yum install python-mutagen mid3iconv -e GBK *.mp3 2. totem电影播放机播放列表乱码解决1).修改to ...

  4. 【leetcode】122.Best Time to Buy and Sell Stock II(股票问题)

    You are given an integer array prices where prices[i] is the price of a given stock on the ith day. ...

  5. 容器之分类与各种测试(四)——unordered-multiset

    unordered-multiset是不定序关联式容器,其底部是通过哈希表实现功能. (ps:黑色框就是bucket,白色框即为bucket上挂载的元素) 为了提高查找效率,bucket(篮子)的数量 ...

  6. C++一元多项式求导

    这个题难度不大但是坑有点多,要考虑的点有几个: 1.测试用例为x 0 这个直接输出 0 0即可. 2.注意空格的输出 3.测试点3我好几次都没过,最后参考了别的答案加以修改才通过. 测试点3没过的代码 ...

  7. centos7安装Docker详细步骤(无坑版教程)

    一.安装前必读 在安装 Docker 之前,先说一下配置,我这里是Centos7 Linux 内核:官方建议 3.10 以上,3.8以上貌似也可. 注意:本文的命令使用的是 root 用户登录执行,不 ...

  8. 【编程思想】【设计模式】【行为模式Behavioral】Specification

    Python版 https://github.com/faif/python-patterns/blob/master/behavioral/specification.py #!/usr/bin/e ...

  9. redis的总结笔记

    # Redis    1. 概念: redis是一款高性能的NOSQL系列的非关系型数据库        1.1.什么是NOSQL            NoSQL(NoSQL = Not Only ...

  10. 【C/C++】n皇后问题/全排列/递归/回溯/算法笔记4.3

    按常规,先说一下我自己的理解. 递归中的return常用来作为递归终止的条件,但是对于返回数值的情况,要搞明白它是怎么返回的.递归的方式就是自己调用自己,而在有返回值的函数中,上一层的函数还没执行完就 ...