(TIỂU LUẬN) implement IDS system integrating machine learning for hai dang travel company

CAPSTONE PROJECT 2Implement IDS system integrating machine learning for Hai Dang Travel company C2NE.02 1... We came up with a solution to deploy an IDS system with machine learning to d

CAPSTONE PROJECT 2

Implement IDS system integrating machine

learning for Hai Dang Travel company

C2NE.02

1

OUR TEAM

Mentor Assoc Prof.

Nhu, Nguyen Gia

Duong

Ngoc The

2

N OBJECTIVES

3

Introduction

4

5

HAI DANG TRAVEL

COMPANY

6

s

HAI DANG TRAVEL

our success

abroad

PROBLEM

Upgrade your network, warn

and prevent attacks

8

We came up with a solution to deploy an IDS

system with machine learning to detect and

prevent attacks

10

PROJECT OBJECTIVES

 Research new approaches for intrusion detection does not depend

on signatures.

 Build an Intrusion Detection System.

 Prevent intrusion

12

PRODUCT OVERVIEW

An intrusion detection LEARNING

Machine learning is the

system (IDS) is a device study of computer

or software application algorithms that improve

that monitors a network automatically through

or systems for malicious experience It is seen as

activity or policy a subset of artificial

violations intelligence

DATASET

A data set consists ofroughly twocomponents The two

components are rows

OPERATION DIAGRAM

14

Company local network diagram

Hai Dang Travel

Network diagram 15

An overview of Logical Network

Diagram

Network diagram with the appearance of IDS

16

Intrusion Detection System Operation

How IDS

work ?

Intrusion Detection System Operation17

Intrusion Detection System Operation

How Machine Learning Model

Works

?

Machine Learning Model Operation 18

DATA PROCESSING

19

DATA PROCESSING

CSE-CIC-IDS2018 dataset

provided by the Canadian

Institute for Cybersecurity Datasets

Realistic background trafficand different attack scenarios

DATA PROCESSING

Datasets Overview

21

Number of flow per attack type

22

DATA PROCESSING

Datasets Problems

23

Data cleaning and features engineering

Remove Replace infinity

duplicate header value to mean

Drop all null and

negative value

Remove strong correlation features

24

Remove strong correlation features

Before After

25

Machine Learning

Gradient Boosting

26

Machine Learning

Gradient Boosting

27

1396.0847661.98322469

flow_duration

8821.24900864048571.59

label

MaliciousBenign

Build Decision Tree from data

28

GRADIENT

BOOSTING

29

GRADIENT

BOOSTING

30

PRODUCT DEMO

31

CONCLUSION In this project, we tried our best and

finished it However, there are stillsome issues that need to be improved

in the latest updates In addition, ourproject has received a lot of positivecontributions from internationalfriends through GitHub

32