‘‘‘
FWAF?-?Machine?Learning?driven?Web?Application?Firewall
Author:?Faizan?Ahmad
Performance?improvements:?Timo?Mechsner
Website:?http://fsecurify.com
‘‘‘

from?sklearn.feature_extraction.text?import?TfidfVectorizer
import?os
from?sklearn.cross_validation?import?train_test_split
from?sklearn.linear_model?import?LogisticRegression
from?sklearn?import?metrics
import?urllib.parse

import?matplotlib.pyplot?as?plt

def?loadFile（name）:
????directory?=?str（os.getcwd（））
????filepath?=?os.path.join（directory?name）
????with?open（filepath‘r‘）?as?f:
????????data?=?f.readlines（）
????data?=?list（set（data））
????result?=?[]
????for?d?in?data:
????????d?=?str（urllib.parse.unquote（d））???#converting?url?encoded?data?to?simple?string
????????result.append（d）
????return?result

badQueries?=?loadFile（‘badqueries.txt‘）
validQueries?=?loadFile（‘goodqueries.txt‘）

badQueries?=?list（set（badQueries））
validQueries?=?list（set（validQueries））
allQueries?=?badQueries?+?validQueries
yBad?=?[1?for?i?in?range（0?len（badQueries））]??#labels?1?for?malicious?and?0?for?clean
yGood?=?[0?for?i?in?range（0?len（validQueries））]
y?=?yBad?+?yGood
queries?=?allQueries

vectorizer?=?TfidfVectorizer（min_df?=?0.0?analyzer=“char“?sublinear_tf=True?ngram_range=（13））?#converting?data?to?vectors
X?=?vectorizer.fit_transform（queries）

X_train?X_test?y_train?y_test?=?train_test_split（X?y?test_size=0.2?random_state=42）?#splitting?data

badCount?=?len（badQueries）
validCount?=?len（validQueries）

lgs?=?LogisticRegression（class_weight={1:?2?*?validCount?/?badCount?0:?1.0}）?#?class_weight=‘balanced‘）
lgs.fit（X_train?y_train）?#training?our?model

##############
#?Evaluation?#
##############

predicted?=?lgs.predict（X_test）

fpr?tpr?_?=?metrics.roc_curve（y_test?（lgs.predict_proba（X_test）[:?1]））
auc?=?metrics.auc（fpr?tpr）

print（“Bad?samples:?%d“?%?badCount）
print（“Good?samples:?%d“?%?validCount）
print（“baseline?Constant?negative:?%.6f“?%?（validCount?/?（validCount?+?badCount）））
print（“------------“）
print（“Accuracy:?%f“?%?lgs.score（X_test?y_test））??#checking?the?accuracy
print（“Precision:?%f“?%?metrics.precision_score（y_test?predicted））
print（“Recall:?%f“?%?metrics.recall_score（y_test?predicted））
print（“F1-Score:?%f“?%?metrics.f1_score（y_test?predicted））
print（“AUC:?%f“?%?auc）

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2017-05-15?00:24??Fwaf-Machine-Learning-driven-Web-Application-Firewall-master\
?????文件??????????65??2017-05-15?00:24??Fwaf-Machine-Learning-driven-Web-Application-Firewall-master\.gitignore
?????文件?????????294??2017-05-15?00:24??Fwaf-Machine-Learning-driven-Web-Application-Firewall-master\README.md
?????文件?????3374922??2017-05-15?00:24??Fwaf-Machine-Learning-driven-Web-Application-Firewall-master\badqueries.txt
?????文件??????296126??2017-05-15?00:24??Fwaf-Machine-Learning-driven-Web-Application-Firewall-master\firewall_fsecurify.jpg
?????文件????24063954??2017-05-15?00:24??Fwaf-Machine-Learning-driven-Web-Application-Firewall-master\goodqueries.txt
?????文件????????2276??2017-05-15?00:24??Fwaf-Machine-Learning-driven-Web-Application-Firewall-master\script.py