web安全之机器学习入门——3.2 决策树与随机森林

目录

简介

决策树简单用法

决策树检测P0P3爆破

决策树检测FTP爆破

随机森林检测FTP爆破

---

简介

决策树和随机森林算法是最常见的分类算法；

决策树，判断的逻辑很多时候和人的思维非常接近。

随机森林算法，利用多棵决策树对样本进行训练并预测的一种分类器，并且其输出的类别是由个别决策树输出的类别的众数决定。

---

决策树简单用法

使用sklearn自带的iris数据集

# -*- coding: utf-8 -*-
from sklearn.datasets import load_iris
from sklearn import tree
import pydotplus
"""
如果报错GraphViz's executables not found，手动添加环境变量
"""
import os
os.environ["PATH"] += os.pathsep + 'D:/Program Files (x86)/Graphviz2.38/bin/'  #注意修改你的路径

iris = load_iris()

clf = tree.DecisionTreeClassifier()
clf = clf.fit(iris.data, iris.target)

#可视化训练得到的决策树
dot_data = tree.export_graphviz(clf, out_file=None)
graph = pydotplus.graph_from_dot_data(dot_data)
graph.write_pdf("../photo/6/iris.pdf")

---

决策树算法检测P0P3爆破

# -*- coding:utf-8 -*-

import re
from sklearn import cross_validation
from sklearn import tree
import pydotplus
import os
os.environ["PATH"] += os.pathsep + 'D:/Program Files (x86)/Graphviz2.38/bin/'  #注意修改你的路径

"""
收集并清洗数据
"""
def load_kdd99(filename):
    x=[]
    with open(filename) as f:
        for line in f:
            line=line.strip('
')
            line=line.split(',')
            x.append(line)
    return x

def get_guess_passwdandNormal(x):
    v=[]
    w=[]
    y=[]
"""
筛选标记为guess-passwd和normal且是P0P3协议的数据
"""
    for x1 in x:
        if ( x1[41] in ['guess_passwd.','normal.'] ) and ( x1[2] == 'pop_3' ):
            if x1[41] == 'guess_passwd.':
                y.append(1)
            else:
                y.append(0)
"""
特征化
挑选与p0p3密码破解相关的网络特征以及TCP协议内容的特征作为样本特征
"""
            x1 = [x1[0]] + x1[4:8]+x1[22:30]
            v.append(x1)
    for x1 in v :
        v1=[]
        for x2 in x1:
            v1.append(float(x2))
        w.append(v1)
    return w,y

if __name__ == '__main__':
    v=load_kdd99("../data/kddcup99/corrected")
    x,y=get_guess_passwdandNormal(v)
"""
训练样本
实例化决策树算法
"""
    clf = tree.DecisionTreeClassifier()
    #十折交叉验证
    print(cross_validation.cross_val_score(clf, x, y, n_jobs=-1, cv=10))

    clf = clf.fit(x, y)
    dot_data = tree.export_graphviz(clf, out_file=None)
    graph = pydotplus.graph_from_dot_data(dot_data)
    graph.write_pdf("../photo/6/iris-dt.pdf")

准确率达到99%

[ 0.98637602  1.          1.          1.          1.          1.          1.
  1.          1.          1.        ]

可视化结果

---

决策树算法检测FTP爆破

# -*- coding:utf-8 -*-

import re
import os
from sklearn.feature_extraction.text import CountVectorizer
from sklearn import cross_validation
import os
from sklearn import tree
import pydotplus

"""

"""
def load_one_flle(filename):
    x=[]
    with open(filename) as f:
        line=f.readline()
        line=line.strip('
')
    return line

"""
加载ADFA-LD中的正常样本数据
"""
def load_adfa_training_files(rootdir):
    x=[]
    y=[]
    list = os.listdir(rootdir)
    for i in range(0, len(list)):
        path = os.path.join(rootdir, list[i])
        if os.path.isfile(path):
            x.append(load_one_flle(path))
            y.append(0)
    return x,y

"""
定义遍历目录下文件的函数，作为load_adfa_hydra_ftp_files的子函数
"""
def dirlist(path, allfile):
    filelist = os.listdir(path)

    for filename in filelist:
        filepath = os.path.join(path, filename)
        if os.path.isdir(filepath):
            dirlist(filepath, allfile)
        else:
            allfile.append(filepath)
    return allfile

"""
从攻击数据集中筛选和FTP爆破相关的数据
"""
def load_adfa_hydra_ftp_files(rootdir):
    x=[]
    y=[]
    allfile=dirlist(rootdir,[])
    for file in allfile:
        """
        rootdir下有多个文件，多个文件里又有多个文件
        """
        if re.match(r"../data/ADFA-LD/Attack_Data_Master/Hydra_FTP_d+\UAD-Hydra-FTP*",file):
            x.append(load_one_flle(file))
            y.append(1)
    return x,y



if __name__ == '__main__':
    """
    特征化
    由于ADFA-LD数据集都记录了函数调用的序列，每个文件包含的函数调用序列的个数都不一致
    """
    x1,y1=load_adfa_training_files("../data/ADFA-LD/Training_Data_Master/")
    #x1{2184×833}  y1{833}
    x2,y2=load_adfa_hydra_ftp_files("../data/ADFA-LD/Attack_Data_Master/")
    #x2{524×162} y2{162}

    x=x1+x2
    y=y1+y2
    #x{2184×995} y{955}
    vectorizer = CountVectorizer(min_df=1)
    #min_df如果某个词的document frequence小于min_df，则这个词不会被当作关键词
    x=vectorizer.fit_transform(x)
    x=x.toarray()
    #x{142×955}
    #实例化决策树算法
    clf = tree.DecisionTreeClassifier()
    #效果验证
    print(cross_validation.cross_val_score(clf, x, y, n_jobs=-1, cv=10))


    clf = clf.fit(x, y)
    dot_data = tree.export_graphviz(clf, out_file=None)
    graph = pydotplus.graph_from_dot_data(dot_data)
    graph.write_pdf("../photo/6/ftp.pdf")

[ 1.          0.98019802  0.95        0.97979798  0.96969697  0.88888889
  0.98989899  0.95959596  0.92929293  0.95959596]

---

随机森林算法检测FTP爆破

# -*- coding:utf-8 -*-
#pydotplus只支持决策树
import re
import os
from sklearn.feature_extraction.text import CountVectorizer
from sklearn import cross_validation
import os
from sklearn import tree
from sklearn.ensemble import RandomForestClassifier
import numpy as np


def load_one_flle(filename):
    x=[]
    with open(filename) as f:
        line=f.readline()
        line=line.strip('
')
    return line

def load_adfa_training_files(rootdir):
    x=[]
    y=[]
    list = os.listdir(rootdir)
    for i in range(0, len(list)):
        path = os.path.join(rootdir, list[i])
        if os.path.isfile(path):
            x.append(load_one_flle(path))
            y.append(0)
    return x,y

def dirlist(path, allfile):
    filelist = os.listdir(path)

    for filename in filelist:
        filepath = os.path.join(path, filename)
        if os.path.isdir(filepath):
            dirlist(filepath, allfile)
        else:
            allfile.append(filepath)
    return allfile

def load_adfa_hydra_ftp_files(rootdir):
    x=[]
    y=[]
    allfile=dirlist(rootdir,[])
    for file in allfile:
        if re.match(r"../data/ADFA-LD/Attack_Data_Master/Hydra_FTP_d+\UAD-Hydra-FTP*",file):
            x.append(load_one_flle(file))
            y.append(1)
    return x,y



if __name__ == '__main__':

    x1,y1=load_adfa_training_files("../data/ADFA-LD/Training_Data_Master/")
    x2,y2=load_adfa_hydra_ftp_files("../data/ADFA-LD/Attack_Data_Master/")

    x=x1+x2
    y=y1+y2
    #print(x)
    vectorizer = CountVectorizer(min_df=1)
    x=vectorizer.fit_transform(x)
    x=x.toarray()
    #print(y)
    #选用决策树分类器
    clf1 = tree.DecisionTreeClassifier()
    score=cross_validation.cross_val_score(clf1, x, y, n_jobs=-1, cv=10)
    print('决策树',np.mean(score))
    #选用随机森林分类器
    clf2 = RandomForestClassifier(n_estimators=10, max_depth=None,min_samples_split=2, random_state=0)
    score=cross_validation.cross_val_score(clf2, x, y, n_jobs=-1, cv=10)
    print('随机森林',np.mean(score))

决策树 0.955736173617
随机森林 0.984888688869