Scribd
Upload
12 views

Ahmed Alhakimy

Uploaded by

Humam Al-Dhubhani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views

Ahmed Alhakimy

Uploaded by

Humam Al-Dhubhani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

AI-based Network

Intrusion Detection
System (NIDS)
Table of contents

1: Introduction 6 : Research Plan


2: Problem Statement 7:
:
3: Research Objectives 8:
4: Subproblems
5 : Literature Review
Introduction

Network Intrusion Detection Systems (NIDS) are vital tools for protecting networks from cyber threats.
With the increasing complexity of attacks

the use of artificial intelligence (AI) in these systems has become essential to enhance detection and
response effectiveness.

1
Problem Statement

Despite advancements in intrusion detection


technologies, traditional systems still suffer from high
false positive rates and slow response times

2
Research Objectives : Develop an AI-based
Intrusion Detection
System

Increase
response speed
to attacks

Analyze big data to


improve detection
accuracy.

3
Subproblems :

1. Analyze the 2. Evaluate the


effectiveness of AI performance of the
algorithms in proposed system
detecting intrusions. compared to
traditional systems.

4
Literature Review :
1 Traditional Anti-Intrusion Systems

Traditional NIDS primarily utilize signature-based detection methods, which rely on predefined attack patterns to
identify intrusions. While these systems can effectively detect known threats, they struggle with new or evolving attack
vectors, resulting in high false negative rates. For instance, Sethi et al. (2018) discuss the limitations of signaturebased
systems in dynamic environments, highlighting the need for more adaptive approaches

2 Machine Learning-Based NIDS

The integration of machine learning techniques into NIDS has significantly improved detection
capabilities. Machine learning algorithms analyze network traffic patterns to identify anomalies
indicative of potential intrusions. Research by Ahmed et al. (2016) demonstrates that machine
learning models can achieve higher detection rates and lower false positives compared to traditional
methods. However, challenges such as the quality of training data and feature selection remain
prevalent (Bansal & Kumar, 2021)

5 -1
Literature Review :
3 Intelligent and Adaptive NIDS

Intelligent and adaptive NIDS represent the cutting edge of intrusion detection technology.
These systems leverage real-time data and machine learning to continuously adapt their
detection mechanisms based on emerging threats and user behavior. Dhanabal and Kumar
(2020) highlight that such systems not only improve detection rates but also enhance
response times to attacks. Nonetheless, the use of adaptive systems raises concerns
regarding data privacy and ethical implications (Zarpelão et al., 2017).

5 -2
Research Plan
1 Research Design 2 Research Methodology

The research adopts a mixed- The methodology involves both


methods approach, combining experimental and descriptive
quantitative and qualitative research. The experimental
techniques to provide a component focuses on developing
comprehensive understanding of and testing machine learning models
AI-based NIDS. This design for intrusion detection, while the
allows for the collection of descriptive aspect involves analyzing
numerical data for statistical existing literature and case studies to
analysis, as well as insights from identify best practices and challenges
expert interviews and case in deploying AI-based NIDS
studies to explore the practical
implications of the findings
6
Data Collection

Testing the system compared to other systems


Data Mining: Utilizing existing datasets for training and testing AI
models, ensuring diversity in the types of intrusions analyzed

7
Data Analysis

• Quantitative:
• Analysis using SPSS/R for KPIs like accuracy and precision.
• Qualitative:
• NVivo for thematic analysis of user feedback and expert
opinions.

You might also like