0% found this document useful (0 votes)
23 views16 pages

Mid Sem 1

Uploaded by

tusharadri123
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
23 views16 pages

Mid Sem 1

Uploaded by

tusharadri123
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Project Presentation on

Network Intrusion Analysis and


Detection system

Submitted by-
1. Amit Acharjee 202010007004
2.Anandam Paul 202010007005
3.Sourajit Deb 202010007043
4.Tusharadri Paul 202010007049
5.Kukipriya Kutum 202010007028

Under the Guidance of –


Mrs Maram Smriti , Asst Prof. Dept. of CSE
Department of Computer Science and Engineering
Barak Valley Engineering College, Karimganj
CONTENT

1. Introduction
2. Motivation
3. Literature survey
4. Problem Statement
5. Objective
6. Project status
7. Future Work
8. Conclusion
9. References
2
INTRODUCTION

 In today’s interconnected world, cyber security remains a paramount


concern for organizations of all sizes.
 Network Intrusion Detection System(NIDS) are critical components in
defending against malicious activities
 This project focuses on developing a NIDS using state-of-the-art machine
learning algorithms.
 The primary aim is to improve the accuracy of intrusion detection while
simultaneously reducing false positives.

3
MOTIVATION

 Rising Cyber Threats


 Limitations of Traditional Approaches.
 Potential of machine learning
 Cost of security breaches
 Impact on all levels of organizations.

4
LITERATURE SURVEY

Paper AUTHOR Title Algorithm used


No.

Threat analysis of IoT networks Using


1 Artificial Neural Network Intrusion
Detection System, 2022
.

5
Brief Overview of Papers
NIDS in different systems

 Different systems includes – IoT, WLAN, Data warehouse .

 Lists the various threats mentioned –


• Denial of Service
• Malware
• Data breaches

6
 Papers contain few techniques used for network intrusion detection –
• Statistical Analysis: Compares current data trends to baseline data set
• Protocol verification: Checks if the data provided defies any protocol
or not.
• ANN model : Undergoes training using feedback to learn the pattern.

7
8

Paper no. Author Title Algorithm mentioned

Ansam Khraisat , Survey of intrusion 1. Signature based


Iqbal Gondal, Peter detection systems (IDS) : intrusion detection
Vamplew and techniques, datasets and system
Joarder challenges, 2019 Anomaly based intrusion
Kamruzzaman detection system-
 Statistics based algorithm
 Machine learning
algorithm
 Knowledge based
algorithm

Nutan Farah , Abdur Application of Machine 1. Single classifier- SVM,


Rahman Onik, Md. Learning Approaches in Fuzzy logic, decision
Avishek Khan Hridoy, Intrusion Detection trees, etc.
Musharrat Rafni, System(IDS) : A Survey, 2. Hybrid classifiers –
Faisal Muhammad, 2015 Combination of two or
Dewan Md. Farid
more machine learning
algorithm.
3. Ensemble classifiers –
Combination of weak
learning models
Brief overview of paper
A survey of IDS and IDS using
machine learning

 Two types of intrusion detection systems –


• Signature based IDS – Detects intrusion based on
previous intrusion types.
• Anomaly based IDS – Detects intrusion based on
anomalies in data.
 Anomaly based IDS divided further into 3 categories –
• Statistical based IDS – Uses probability distribution
to detect anomalies.
• Knowledge based IDS – Uses training models
trained with human knowledge to detect anomalies.
• Machine learning based IDS – Uses Machine
learning algorithms to detect anomalies. 9
 Intrusion detection system using Machine learning has mainly 3
types -
• Single Classifier: Uses single algorithms like Decision Trees, Naïve
Bayes, SVM, ANN, K- nearest neighbors to detect intrusion.
• Hybrid classifiers: Uses combination of two or more algorithms to
detect intrusion.
• Ensemble Classifier: Uses combination of weak learners to detect
intrusion.

Intrusion detection using


Machine Learning
Figure 2
10
Problem Statement

 Inadequate detection accuracy.


 Limited Scalability.
 Delayed Response times.
 False positives and alert fatigues
 Integration with existing security Infrastructure

11
OBJECTIVE

 To understand the working of NIDS.


 To apply the concept of Machine learning for NIDS.
 To improve detection accuracy.
 To compare our developed system with existing ones using
various parameters

12
PROJECT STATUS

 Completed studying research papers related to Network Intrusion Detection


System (NIDS).

 Summarized various algorithms used for making NIDS.

 Checking the feasibility of each algorithm.

13
FUTURE SCOPE

 Selecting the algorithms based on their feasibility.


 Making the design on the basis of the selected algorithm
 Creating the interface on the basis of design.
 Creating the system to using the algorithm.

14
REFERENCES

15
26

THANK YOU

You might also like