Consult an Expert
Trademark
Design Registration
Consult an Expert
Trademark
Copyright
Patent
Infringement
Design Registration
More
Consult an Expert
Consult an Expert
Trademark
Design Registration
Login
DETECTING PHISHING AND MALICIOUS URLS USING LOGISTIC REGRESSION MODELS
Extensive patent search conducted by a registered patent agent
Patent search done by experts in under 48hrs
₹999
₹399
Abstract
Information
Inventors
Applicants
Specification
Documents
ORDINARY APPLICATION
Published
Filed on 23 November 2024
Abstract
This invention provides a method for detecting malicious URLs using logistic regression by classifying URLs based on features indicative of threat levels. It enables real-time detection by continuously analyzing URL patterns and blocking those identified as malicious. This dynamic, machine-learning-based system improves online security and adapts to new cyber threats through periodic model updates. The rise of mobile devices has driven Real world activities online, exposing users to the growing threat of malicious URLs that can compromise network security by distributing malware, launching phishing attacks, and causing data breaches. This paper proposes using logistic regression, a powerful binary classification tool, to differentiate between malicious and benign URLs. By extracting and analyzing features such as character sequences, suspicious keywords, and specific subdomains, the logistic regression model can identify patterns indicative of malicious intent. Although effective, logistic regression's assumption of linearity between features and maliciousness poses a limitation, as cybercriminals employ complex strategies that may avoid detection. Therefore, while logistic regression offers interpretability and initial success, enhancing this approach with advanced machine learning techniques could provide deeper insights and more robust protection against cyber threats.
Patent Information
Application ID | 202441091344 |
Invention Field | COMPUTER SCIENCE |
Date of Application | 23/11/2024 |
Publication Number | 48/2024 |
Inventors
Name | Address | Country | Nationality |
---|---|---|---|
B.USHA SRI | Department of Computer Science and Engineering, B V Raju Institute of Technology, Narsapur, Telangana - 502313. | India | India |
VARUN SINGH BAMLA | Department of Computer Science and Engineering, B V Raju Institute of Technology, Narsapur, Telangana - 502313. | India | India |
VENU BANDARI | Department of Computer Science and Engineering, B V Raju Institute of Technology, Narsapur, Telangana - 502313. | India | India |
MANIKANTA BHEEMAGANTI | Department of Computer Science and Engineering, B V Raju Institute of Technology, Narsapur, Telangana - 502313. | India | India |
CHAITANYA UPPUGANTI | Department of Computer Science and Engineering, B V Raju Institute of Technology, Narsapur, Telangana - 502313. | India | India |
RUTHVIK AKKENAPALLY | Department of Computer Science and Engineering, B V Raju Institute of Technology, Narsapur, Telangana - 502313. | India | India |
Applicants
Name | Address | Country | Nationality |
---|---|---|---|
B V Raju Institute of Technology | Department of Computer Science and Engineering, B V Raju Institute of Technology, Narsapur, Telangana - 502313. | India | India |
Specification
Description:Field of the Invention:
The present invention relates to the field of cybersecurity and machine learning. Specifically, it pertains to a method for detecting malicious URLs by using logistic regression to classify URLs based on features indicative of potential threats. This invention provides a real-time detection system for online security applications.
Background of the Invention:
As the internet grows, malicious URLs have become a significant cybersecurity threat, leading to phishing attacks, malware infections, and data breaches. Traditional URL detection relies on blacklists, which are often inadequate for identifying new and emerging threats. Consequently, there is a need for a machine learning-based approach to detect and classify URLs dynamically. Logistic regression, a method well-suited for binary classification, can use specific URL features to distinguish between malicious and benign URLs effectively.
Summary of the Invention:
The present invention provides a method for malicious URL detection using logistic regression, comprising the following steps:
Data Collection: Collecting a labeled dataset of URLs, including both malicious and benign URLs.
Feature Extraction: Extracting URL features such as length, domain reputation, special character usage, and IP-based domains.
Model Training: Training a logistic regression model on these features to classify URLs.
Real-Time Detection: Deploying the model to classify URLs in real-time and flagging suspicious URLs for blocking or further action.
System Benefits: Enhancing cybersecurity by providing a scalable, efficient, and accurate solution for URL threat detection.
Detailed Description of the Invention:
Step 1: Data Collection
A dataset containing labeled URLs (malicious and benign) is compiled from reliable sources such as cybersecurity threat databases.
Step 2: Feature Extraction
Features critical for detection are extracted, including URL length, domain age, IP usage, and presence of special characters. These features form a vector used to train the model.
Step 3: Model Training
The logistic regression model is trained using labeled data to optimize the weights for each feature, allowing the model to classify URLs as malicious or benign with high accuracy.
Step 4: Real-Time Detection
In a deployed environment, URLs are analyzed in real-time, and the model assigns a probability score for each URL. URLs that exceed a certain risk threshold are flagged as malicious.
Step 5: Adaptability and Updating
The system is periodically updated with new data, and the model is retrained to handle emerging threats.
, Claims:Claim 1: A method for malicious URL detection using logistic regression,
comprising: Collecting and labeling a dataset of URLs as malicious or
benign. Extracting features from URLs. Training a logistic regression model
using these features. Deploying the model for real-time detection.
Claim 2: The method of claim 1, where extracted features include URL
length, domain reputation, use of special characters, IP-based domains, and
HTTPS status.
Claim 3: A real-time detection system, as claimed in claim 1, designed to
block or flag URLs classified as malicious based on a predefined probability
threshold.
Claim 4: A system for dynamic model updating, as claimed in claim 1,
where new data is incorporated periodically to maintain detection accuracy.
Claim 5: The malicious URL detection system, as claimed in claim 1,
configured for deployment across web browsers, network systems
cybersecurity applications.
Documents
Name | Date |
---|---|
202441091344-COMPLETE SPECIFICATION [23-11-2024(online)].pdf | 23/11/2024 |
202441091344-DECLARATION OF INVENTORSHIP (FORM 5) [23-11-2024(online)].pdf | 23/11/2024 |
202441091344-FORM 1 [23-11-2024(online)].pdf | 23/11/2024 |
202441091344-REQUEST FOR EARLY PUBLICATION(FORM-9) [23-11-2024(online)].pdf | 23/11/2024 |
Talk To Experts
Calculators
Downloads
By continuing past this page, you agree to our Terms of Service,, Cookie Policy, Privacy Policy and Refund Policy © - Uber9 Business Process Services Private Limited. All rights reserved.
Uber9 Business Process Services Private Limited, CIN - U74900TN2014PTC098414, GSTIN - 33AABCU7650C1ZM, Registered Office Address - F-97, Newry Shreya Apartments Anna Nagar East, Chennai, Tamil Nadu 600102, India.
Please note that we are a facilitating platform enabling access to reliable professionals. We are not a law firm and do not provide legal services ourselves. The information on this website is for the purpose of knowledge only and should not be relied upon as legal advice or opinion.