Home / Current Issue / Paper 1707096
SafeNet Shield: Finding illegal websites using RNN-GRU and inappropriate messages using Logistic Regression, Decision Tree & Random Forest
Subject area: Science,Engineering and Technology · Area of research: Computer Science
Abstract
SafeNet Shield aims to enhance online safety by detecting phishing websites and cyberbullying messages, leveraging machine learning and deep learning techniques for accurate detection using RNN-GRU models and Random Forest, Decision Trees, and Logistic Regression. The system provides real-time detection and feedback through a user-friendly interface, addressing limitations of existing approaches, promoting a safer digital environment, mitigating online risks, and is scalable, efficient, and accessible. Built using HTML, CSS, Tailwind CSS, and Django, its objective is to reduce cyber threats, promote digital well-being, and contribute to secure online interactions and digital safety solutions. The project's scope includes developing a comprehensive system for online threat detection.
Keywords
Phishing, Cyberbullying, RNN-GRU Models, Random Forest, Decision Trees, Logistic Regression
References
[1] Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition
[2] Lizhen Tang and Qusay h. Mahmoud, “A Deep Learning-Based Framework for Phishing Website Detection”, IEEE Access, 2022.
[3] Teoh Hwai Teng, Kasturi Dewi Varathan,“Cyberbullying Detection in Social Networks: A Comparison Between Machine Learning and Transfer Learning Approaches”, IEEE Access, 2023.
[4] Hadiya E M, “Cyber Bullying Detection in Twitter using Machine Learning Algorithm”, 2022.
[5] Mohammed Hazim Alkawaz, Stephanie Joanne Steven, Asif Iqbal Hajamydeen, Rusvaizila Ramli, “A Comprehensive Survey on Identification and Analysis of Phishing Websites Based on Machine Learning Methods”,2021.
[6] Abdul Basit, Maham Zafar, Abdul Rehman Javed, Zunera Jalil,“A Novel Ensemble Machine Learning Method to Detect Phishing Attacks”,2020.
[7] Š‹Œ”•—¥¦¨¼½ËÌÍÎÔÕõ÷) * + , ñßñÐƼ°£¼°£¼°›’‡ynyeYeYMMh^~ CJOJQJaJh^~ h^~ 6�OJQJh9wþ6�OJQJh9wþ6�H*OJQJh^~ h^~ 6�H*OJQJh^~ h^~ OJQJh9wþH*OJQJh9wþOJQJh^~ h^~ OJPJQJh^~ h^~ H*OJQJh9wþOJPJQJhE@[OJPJQJh%-h^~ CJ(OJPJQJ"h%-h9wþ6�CJ(OJQJ]�aJ(h%-h9wþCJ(OJQJaJ(‹ŒÍ* + , - QR¾¿ÌÍòÝÝȳ¡¡–ŒŒŒwŒ$ &F„7„Éý¤^„7`„Éýa$gdE@[ $¤a$gdE@[ $da$gdE@[„ñÿ„ dð¤]„ñÿ^„ gd^~ $„ñÿ„ dð¤]„ñÿ^„ a$gd^~ $„ñÿ„ dð¤]„ñÿ^„ a$gd˜g$„`„öÿdë¤^„``„öÿa$gd˜g$dݤa$gdE@[ [Some characters in this reference could not be displayed correctly — please refer to the published PDF for the full reference.]
[8] , - 5 7 -PQRWY_az¼½¾¿ËÌñããÕÕÕɉyl\L<hE@[h˜gCJOJQJ\�aJhE@[h^~ CJOJQJ\�aJhE@[hE@[CJOJQJ\�aJhR0·CJOJQJ\�aJhE@[hR0·CJOJQJ\�aJ"hE@[hR0·5�6�CJOJQJaJ&hE@[hE@[5�6�CJOJPJQJaJ&hE@[h^~ 5�6�CJOJPJQJaJ"hE@[h^~ 5�6�CJOJQJaJhE@[hR0·5�6�CJaJhE@[h^~ 5�6�CJaJh^~ h˜gCJOJQJaJÌÍÍsÍSTT^_pqrr…††¸¹ÄÅÆîÚÚÚÚîÚÚîÚɵ£“…tt…ttdRdBhE@[hE@[CJOJQJ\�aJ#hE@[h~l¼CJOJPJQJ\�aJhE@[h~l¼CJOJQJ\�aJ hE@[h~l¼B*CJ\�aJphhE@[B*CJ\�aJphhE@[h^~ CJOJQJ\�aJ#hE@[hÿQKCJOJPJQJ\�aJ'hE@[hE@[CJOJQJ\�aJmH @sH @!h“PHCJOJQJ\�aJmH @sH @'hE@[h“PHCJOJQJ\�aJmH @sH @!hE@[CJOJQJ\�aJmH @sH @ÍsSTö_qr…†¸¹ÅÆÖP ( õõõõõõõàÎÎÎÎõàįÎÎõõ$ &F „„äþ¤^„`„äþa$gdE@[ $¤a$gdE@[$d$ &F„7„Éý¤^„7`„Éýa$gdE@[ $¤a$gdE@[ÆÕÖÖPÖ ( "6"7"8"C"D",#-#.#0#I#D$Z%[%\%y%ìÜËËË˺ÜÜÜ �}mmmmZZJJJZZhE@[hˆa@CJOJQJ\�aJ%hE@[hˆa@6�CJOJQJ\�]�aJhE@[h®sïCJOJQJ\�aJ%hE@[h´]h6�CJOJQJ\�]�aJhE@[hE@[CJOJQJ\�aJhQU²CJOJQJ\�aJhE@[CJOJQJ\�aJ hE@[h´]hB*CJ\�aJph hE@[hQU²B*CJ\�aJphhE@[hQU²CJOJQJ\�aJ&hE@[hQU²6�CJOJPJQJ\�aJ( 7"8"D"-#.#I#[%\%y%›%¿%ô%#&P&Q&n&p&q&†&õõàõõõõõõõÇÇÇǽ½½õ¨$ &F„7„Éý¤^„7`„Éýa$gdE@[ $¤a$gdE@[$ &F [Some characters in this reference could not be displayed correctly — please refer to the published PDF for the full reference.]
How to cite this paper
@article{1707096,
author = {Tarani S, Sadiya Kaunain, Alice Patricia Innes, Shawn Thomas},
title = {SafeNet Shield: Finding illegal websites using RNN-GRU and inappropriate messages using Logistic Regression, Decision Tree & Random Forest},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {8},
number = {8},
pages = {335-339},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1707096.pdf},
abstract = {SafeNet Shield aims to enhance online safety by detecting phishing websites and cyberbullying messages, leveraging machine learning and deep learning techniques for accurate detection using RNN-GRU models and Random Forest, Decision Trees, and Logistic Regression. The system provides real-time detection and feedback through a user-friendly interface, addressing limitations of existing approaches, promoting a safer digital environment, mitigating online risks, and is scalable, efficient, and accessible. Built using HTML, CSS, Tailwind CSS, and Django, its objective is to reduce cyber threats, promote digital well-being, and contribute to secure online interactions and digital safety solutions. The project's scope includes developing a comprehensive system for online threat detection.},
keywords = {Phishing, Cyberbullying, RNN-GRU Models, Random Forest, Decision Trees, Logistic Regression},
month = {February},
}