You are on page 1of 3

Malicious Url Detection Based

on Machine Learning
Balamurugan Vasanth P Grihith S Youkesh G
Department of Computer Department of Computer Department of Computer Department of Computer
Science and Engineering Science and Engineering Science and Engineering Science and Engineering
Sri Sairam Engineering Sri Sairam Engineering Sri Sairam Engineering Sri Sairam Engineering
College College College College
Chennai,India Chennai,India Chennai,India Chennai,India
line 5: email address or line 5: email address or Gririhith907@gmail.com Youkeshganesan1103@gm
ORCID ORCID ail.com

Abstract—The rapid growth of open networks and increased activities. However, this growing dependence has given rise to a
societal dependence on them have given rise to new cyber threats, multitude of cyber threats and information security issues,
particularly the alarming prevalence of sniffing attacks. These posing significant challenges for individuals and organizations
malicious activities exploit vulnerabilities in network systems, alike. One of the most critical and prevalent attacks is the
tricking unsuspecting users and compromising sensitive exploitation of malicious URLs, particularly through sniffing
information. The consequences are staggering, with billions of techniques, aimed at extracting unsolicited information. These
dollars lost each year due to these attacks. Therefore, the need to attacks often target inexperienced end users, tricking them into
secure websites and detect sniffing attacks has become paramount. accessing malicious links that compromise their systems and
In this project, we propose an advanced sniffing detection system lead to substantial financial losses. The impact of such attacks
that combines machine learning algorithms, behavioural analysis, includes risks like data theft, financial fraud, privacy breaches,
and anomaly detection techniques. Our solution operates at both and unauthorized system access. These incidents collectively
the network and application levels, providing comprehensive result in billions of dollars lost each year. Given the alarming
protection against various types of sniffing techniques. Through consequences and the accelerating pace of these threats, it has
deep packet inspection, behavioural analysis, and application-level become imperative to enhance website security measures.
analysis, our system can identify and mitigate sniffing attacks in Therefore, the focus of this project is to develop effective
real-timeKey features of our solution include real-time alerts, techniques for detecting and mitigating malicious URLs. By
automated response actions, seamless integration with existing addressing this problem, we aim to safeguard users from falling
security infrastructure, and a user-friendly interface for easy victim to
configuration and management. We have collected a diverse these deceptive tactics, protecting their sensitive information,
dataset of 30,000 URLs for training and testing, and our feature and reducing the financial losses incurred due to cybercriminal
extraction module utilizes over 20 user-defined functions to assess activities..
the maliciousness of URLs accurately. By developing and
implementing our sniffing detection solution, organizations can III METHODOLOGY
proactively safeguard their systems, prevent financial losses, and
protect sensitive data from falling into the wrong hands. Our
solution represents a crucial step in securing open networks,
ensuring the integrity of information, and mitigating the risks
associated with sniffing attacks

Keywords—component, formatting, style, styling, insert (key


words)

I. INTRODUCTION
The rapid growth of open networks and increased societal
dependence on them have given rise to new cyber threats,
particularly the alarming prevalence of sniffing attacks. These
malicious activities exploit vulnerabilities in network systems,
tricking unsuspecting users and compromising sensitive
information. The consequences are staggering, with billions of III. MODULE DESCRIPTION
dollars lost each year due to these attacks. Therefore, the need to After the text edit has been completed, the paper is ready for
secure websites and detect sniffing attacks has become the template. Duplicate the template file by using the Save As
paramount . In this project, we propose an advanced sniffing command, and use the naming convention prescribed by your
detection system that combines machine learning algorithms, conference for the name of your paper. In this newly created
behavioral analysis, and anomaly detection techniques. Our file, highlight all of the contents and import your prepared text
solution operates at both the network and application levels, file. You are now ready to style your paper; use the scroll down
providing comprehensive protection against various types of window on the left of the MS Word Formatting toolbar.
sniffing techniques. Through deep packet inspection, behavioral
analysis, and application-level analysis, our system can identify
and mitigate sniffing attacks in real-time. Key features of our
solution include real-time alerts, automated response actions, A. Module1: Dataset Collection
seamless integration with existing security infrastructure, and a • In this module, the primary goal is to collect the necessary
user-friendly interface for easy configuration and management . datasets for training and testing the malicious URL detection
system.
II. PROBLEM STATEMENT • Collecting a diverse and representative dataset is crucial for
In today's increasingly interconnected world, societies training an effective model.
heavily rely on open networks, such as the internet, for various The dataset includes a collection of both malicious and benign
URLs.
These URLs are sourced from various reliable and relevant
sources, such as security databases, online forums, or previous
research studies.
• The dataset used for the prototype development consists of
30,000 URLs, providing a substantial amount of data for training
and evaluation.

'IV RESULT

B. Module 2: Feature Extraction


The feature extraction module focuses on extracting relevant
features from the URLs to determine their maliciousness.
• Various features can help identify patterns and characteristics
commonly found in malicious URLs.
• This module employs more than 20 user-defined functions that
extract different features from the URLs. These functions may
include analyzing the length of the URL, presence of suspicious
characters, domain reputation, use of redirection, or the
presence of specific keywords.
• The extracted features serve as valuable indicators for the
subsequent analysis and classification of URLs as malicious or
benign.

C. Module 3: Training and Testing


The training and testing module involves the core process of
training the malicious URL detection system and evaluating its
performance.

• Using the collected dataset, the system undergoes a training


phase to learn and identify patterns that differentiate
malicious URLs from benign ones
REFERENCES
•The training process employs machine learning algorithms or 1. Sultan Asiri, Yang Xiao, “A Survey of Intelligent
other classification techniques Manuel Sánchez-Paniagua, Eduardo Fidalgo
Fernández, “Phishing URL Detection: A R Real Case
• The trained model is then tested using various evaluation Scenario Through Login URLs”, IEEE, 2022
metrics to assess its accuracy, precision, recall, or F1 score. 2. Detection Designs of HTML URL Phishing Attacks”,
IEEE, 2023
3. Saleem Raja A, Madhubala R, “Survey on Malicious
URL Detection Techniques”, IEEE, 2022
4. Malak Aljabri, Hanan S. Altamimi, “Detecting
Malicious URLs Using Machine Learning Techniques
Review and Research Directions”, IEEE, 2022
5. Vedanti Dantwala, Rishi Lakhani, “A Novel Technique
to Detect URL Phishing based on Feature Count”,
IEEE, 2023
6. Areti Nagendra Soma Charan, Yu-Hung Chen,
“Phishing Websites Detection using Machine Learning
with URL Analysis”, IEEE, 2022
7. Kiruthi Whasan W R, Khiran Khumhaar W R, “Web
Extension for Phishing URL Identification”, IEEE,
2022
8. Rashmi Jha, Gaurav Kunwar, “Machine Learning based
URL Analysis for Phishing Detection”, IEEE, 2023
9. Prakash Pathak; Akhilesh Kumar Shrivas,”
Classification o Phishing Website Using Machine
Learning Based Proposed Ensemble Model”, IEEE,
2023

You might also like