Search In this Thesis
   Search In this Thesis  
العنوان
Enhanced intrusion detection technique for improving security in computing environment /
المؤلف
Yaseen, Humam Khalid.
هيئة الاعداد
باحث / همام خالد ياسين
مشرف / مجدى زكريا رشاد
مشرف / شريهان محمد أبوالعينين
مناقش / ياسر عبداللطيف
مناقش / أميمة محمد نمير
الموضوع
Computer science. Computers - Access control. Computer networks - Security measures. Computer security.
تاريخ النشر
2016.
عدد الصفحات
99 p. :
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
Computer Science (miscellaneous)
تاريخ الإجازة
1/1/2016
مكان الإجازة
جامعة المنصورة - كلية الحاسبات والمعلومات - Computer Science
الفهرس
Only 14 pages are availabe for public view

from 32

from 32

Abstract

Because using the internet and the high usage of transferring data over networks, the term Intrusion raised which can be defined as the attempt to attack and break Information Systems and Networks. For that reason we must construct a system to protect our systems and networks, this system called (Intrusion Detection System), an intrusion detection system (IDS) is a software application that monitors network or system activities for pernicious activities. Many researchers work on intrusion detection and some of them propose systems based on machine learning techniques, but some of them didn’t introduce high detection or decrease the time, in addition to that they depend on just one algorithm on their proposed intrusion detection systems. In our proposed system, we make some operation on the data set to enhance some criteria, which are described as follows: depending on data mining technique we made feature reduction using correlation feature subset selection with best first search evaluator in order to reduce uncorrelated features from processing, reducing the total number of used attributes for classification process is helpful for enhancing time, memory and other resource optimization, after that we made a data splitter in order to obtain training data set with 66% from original data set, and the remain 34% is allocated for the test data set . After that construct our system applies three algorithms, these algorithms: discernibility classifier based k-nearest, J48 decision tree and Naïve Bayes rule, are used to discover any intrusion based on anomaly detection. Our system depends on the concept of decision level fusion. There are two different suggested framework in this thesis. The first called Directive Decision model, this model applies the maximum protection by making the decision anomaly if any decision of the three algorithms is anomaly. The second framework depending on the similarity of decisions between the three algorithms and choose the most frequent among them.