Detecting DDoS attack using a multilayer data mining techniques

Other Title(s)

طريقة لمنع هجمات الحرمان الموزعة باستخدام آليات التنقيب عن البيانات

Dissertant

al-Biltaji, Hibah Saqr Mahmud

Thesis advisor

Barhum, Tawfiq Sulayman

Comitee Members

al-Agha, Iyad Muhammad
Fatayir, Tamir Sad

University

Islamic University

Faculty

Faculty of Information Technology

University Country

Palestine (Gaza Strip)

Degree

Master

Degree Date

2015

English Abstract

Availability is one of the three main components of computer security, along with confidentiality and integrity.

One of the major threats to network security is Denial of Service (DDoS),which is a relatively simple, but very powerful technique to attack internet resources as well as system resources.

Distributed multiple agents consume some critical resources at the target within the short time and deny the service to legitimate clients .

Most current network intrusion detection systems employ signature-based methods or supervised-based methods which rely on labelled training data.

This training data is typically expensive to produce, these methods have difficulty in detecting new types of attack, Using unsupervised anomaly detection techniques , the system can be trained with unlabelled data and is capable of detecting previously “unseen" attacks.

In this research we multi-clustering method using data mining techniques by combination of clustering method (K-Mean(Km) ,K-Medoid(KD),K-Fast Mean(KFM)) as a multi clustering to be able for detecting anew DDoS attacks from unlabelled dataset depend on unsupervised behavior-anomaly detection approach, Davies_Bouldin index(DB) is used to evaluate the proposed method .

The results show that the proposed method has lower davies_bouldin index.

Main Subjects

Information Technology and Computer Science

Topics

• Data protection
• Computers
• Security measures
• Data mining

No. of Pages

49

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-688517