Download as pdf or txt
Download as pdf or txt
You are on page 1of 10

CLASSIFICATION AND MITIGATION OF

CYBER ATTACKS USING MACHINE


LEARNING APPROACH

A PROJECT REPORT

Submitted by

PRANAV.S

SUNDARAM.S

VIGNESH.J

in partial fulfillment for the award of the degree

of

BACHELOR OF TECHNOLOGY

IN

INFORMATION TECHNOLOGY

SRI VENKATESWARA COLLEGE OF ENGINEERING


(An Autonomous Institution; Affiliated to Anna University, Chennai -600 025)

ANNA UNIVERSITY :: CHENNAI 600 025


March 2024

i
SRI VENKATESWARA COLLEGE OF ENGINEERING
(An Autonomous Institution; Affiliated to Anna University, Chennai -600 025)

ANNA UNIVERSITY :: CHENNAI – 600 025

BONAFIDE CERTIFICATE

Certified that this project report “CLASSIFICATION AND MITIGATION OF


CYBER ATTACKS USING MACHINE LEARNING APPORACH” is the
bonafide work of “PRANAV S (2127200801062), SUNDARAM S
(2127200801088), VIGNESH J (21272008010312)” who carried out the project
work under my supervision.

SIGNATURE SIGNATURE
Dr. V. Vidhya, M.E, Ph.D., Ms. R. Saktheeswari, M.E.,
HEAD OF THE DEPARTMENT SUPERVISOR
ASSISTANT PROFESSOR

Department of Information Technology Department of Information Technology


Sri Venkateswara College of Engineering Sri Venkateswara College of Engineering
Post Bag No.1, Pennalur Village, Post Bag No.1, Pennalur Village,
Sriperumbudur (off Chennai) Tk. - 602 117 Sriperumbudur (off Chennai) Tk. - 602 117
Tamil Nadu, India Tamil Nadu, India

Submitted for the project viva-voce examination held on

INTERNAL EXAMINER EXTERNAL EXAMINER


ii
ABSTRACT

The proposed system employs a comprehensive approach to cyberattack classification,

leveraging supervised machine learning techniques to enhance threat detection and

mitigation in cybersecurity. It begins by curating a diverse dataset comprising a wide

range of attack types, from malware and phishing to distributed denial-of-service

(DDoS) attacks, serving as the foundation for training a robust classification model.

Feature extraction techniques are then applied to both network traffic data and

behavioral attributes to identify key features characterizing different attack types. The

system aims to accurately predict attack categories through the use of various supervised

learning algorithms, including decision trees, support vector machines (SVM), and

neural networks. By labeling historical attack instances, the model learns intricate

patterns and nuances inherent in cyberattack behavior, improving its predictive

capabilities over time. Regular updates and retraining with new attack data ensure the

model's continued relevance in dynamic threat landscapes. Empowering cybersecurity

teams with enhanced predictive accuracy, the system enables swift identification and

response to cyber threats, ultimately contributing to proactive threat mitigation and

fortifying digital security frameworks.

iii
ACKNOWLEDGMENT

We thank our principal Dr. Ganesh Vaidyanathan, PhD, Principal, Sri


Venkateswara College of Engineering for being the source of inspiration throughout our
study in this college.

We express our sincere thanks to Dr. V. Vidhya, M.E., PhD., Head of the
Department, Information technology for her permission and encouragement accorded to
carry out this project.

We are also thankful to Dr. G. Sumathi, M.E., PhD., and Dr.


N. Gobalakrishnan, M.Tech., Ph.D., project coordinators for their continual support
and assistance throughout the course of this project.

With profound respect, we express our deep sense of gratitude and sincere thanks
to our guide Ms. R. Saktheeswari, M.E., for her valuable guidance andsuggestions
throughout this project.

We also express our thanks to all Faculty members, Department of Information


Technology, for rendering their support.

PRANAV S
SUNDARAM S
VIGNESH J

iv
TABLE OF CONTENTS

CHAPTER NO TITLE PAGE NO


ABSTRACT iii
LIST OF FIGURES vii
LIST OF TABLES viii
LIST OF ABBRIVATIONS ix
1 INTRODUCTION 1
1.1 OVERVIEW 1
1.2 NETWORK TRAFFIC ANALYSIS 2
1.3 MACHINE LEARNING 2
1.4 CYBER ATTACKS 2
1.5 TYPES OF CYBER ATTACKS 2
1.6 CLASSIFICATION OF ATTACKS 3
1.7 CHALLENGES IN CYBER SECURITY
1.8 EXISTING SYSTEM
1.9 PROPOSED SYSTEM
1.10 ORGANIZATION OF THE PROJECT

2 LITERATURE REVIEW 7
2.1 INTRODUCTION 8
2.2 LITERATURE SURVEY 9

3 SYSTEM DESIGN 13
3.1 INTRODUCTION 13
3.2 DESIGN OF NETWORK TRAFFIC ATTACK 14
CLASSIFICATION SYSTEM
3.3 MODULE DESCRIPTION
3.3.1 Data Preprocessing
v
3.3.2 Feature Selection
3.3.3 Model Selection and Training
3.3.4 Model Evaluation
3.3.5 Deployment
3.4 GAUSSIAN NAIVES BAYES CLASSIFIER
3.5 ADABOOST
3.6 XGBOOST
3.7 RANDOM FOREST CLASSIFIER

4 SYSTEM REQUIREMENTS 21
4.1 HARDWARE REQUIREMENTS 21
4.2 SOFTWARE REQUIREMENTS 22

5 SYSTEM REQUIREMENTS 23
5.1 EXPERIMENTAL SETUP 23
5.2 COMPARISON BETWEEN MACHINE 24
LEARNING ALGORITHMS
5.3 RESULTS 26
5.4 PERFORMANCE EVALUATION
5.5 CLASSIFICATION AND MITIGATION OF
CYBER ATTACKS

6 CONCLUSION AND FUTURE WORK 33


6.1 CONCLUSION 33
6.2 FUTURE WORK 34
7.2 FUTURE WORK 43

REFERENCES 50

vi
LIST OF FIGURES

FIGURE FIGURE NAME PAGE

NO. NO.

4.1 21

5.2 24

5.5 29

7.1 39

7.2 39

7.3 40

7.4 40

7.5 41

7.6 41

7.7 42

7.8 42

7.9 43

vii
LIST OF TABLES

TABLE TABLE NAME PAGE NO.

NO.

6.2 34

6.3 35

viii
LIST OF ABBREVATIONS

ABBREVATION EXPANSION

ix
10

You might also like