There are 4 repositories under url-classification topic.
URI-URL Classification using Recurrent Neural Network, Support Vector and RandomForest. The Implementation results follows with classification report, confusion matrix and precision_recall_fscore_support for each validation result of a 10-fold crossval
To identify and extract features from URL that help classify URLs into benign/phishing and train an ML model with these features for classification.
QuickCharNet is a deep learning project that leverages an efficient character-level Convolutional Neural Network (CNN) for URL classification, aimed at enhancing Search Engine Optimization (SEO). The project includes datasets, model evaluation notebooks, and visualization scripts. Key features include data preprocessing, detailed model architecture
multi-label url classification
Machine Learning model for URL Reputation dataset from UCI ML Repository
URL classification by Naive Bayes algorithm
This repo is the dataset for the paper "A New Dataset and Methodology for Malicious URL Classification"
Proactive Malicious URL Detection: ML Defense 🌐🛡️"
Identifying Suspicious URLs: An Application of Large-Scale Online Learning (Python Reproducibility Experiment)
detect phishing URLs to enhance online security and predict potential threats
Modern, explainable phishing URL detection with FastAPI, policy bands, and LLM-based review. Fast, auditable, and easy to run locally or in Docker.
Multi-label URL Classification
Machine learning system for detecting malicious URLs using Random Forest and Logistic Regression. Features REST API, live dashboard, and Docker deployment.
This project implements a Machine Learning and Deep Learning hybrid approach to detect phishing websites. By analyzing URLs and their associated features, the system predicts whether a given website is legitimate or phishing, leveraging multiple ML algorithms and neural networks for improved accuracy.
An API for URL classification using XGBoost. Identifies whether a URL is benign or malicious based on lexical and host-based features.