A list of malicious IP addresses associated with botnets, cyberattacks, and the generation of artificial traffic on websites. Useful for network administrators and security companies to block threats and protect against DDoS attacks.

Part of BadURL Killer Project aim to protect user from access malicious website

Browser extension that protects you from phishing and malicious websites.

Malware blocklist for Little Snitch

Automated OWASP CRS and Bad Bot Detection for Nginx, Apache, Traefik and HaProxy

🛡️ Aggregate and normalize malicious domains from various sources for effective threat intelligence and cybersecurity defense.

This document provides a comprehensive website security implementation guide designed to protect a WordPress-based production server from high-volume malicious traffic and brute-force attacks.

Machine learning pipeline for malicious URL detection using lexical feature engineering, Random Forest, XGBoost, Logistic Regression, ROC/PR analysis, and cybersecurity ethics.

Part of BadURL Killer Project aim to protect user from access malicious website

The phishing url detector scores 0-100 using 11 red flag heuristiscs(ip address,keywords,https,length etc)

Real-time phishing URL detection app for analyzing and classifying links as safe or malicious using AI and cybersecurity techniques.

Machine learning-based malicious URL detection system for classifying URLs as safe or harmful using feature extraction and predictive modeling.

Technical analysis and incident response report for a credential-harvesting phishing campaign

Machine learning–based phishing URL detection using LightGBM, character n-grams, and structured URL features with a scalable prediction pipeline.

An end-to-end machine learning web application that detects whether a URL is safe or malicious. The project includes a React frontend for URL submission, a Flask backend API for prediction, and a trained NLP-based classification model built with TF-IDF vectorization and Logistic Regression.

A machine learning phishing detection system trained on structured email and URL features. MailHarpoon leverages feature engineering and supervised classification to identify malicious intent in digital communication.

Malicious URL detection with lexical feature engineering, supervised learning, cross-validated model comparison, and test-set evaluation.

# Cyber Epidemic ML A Flask web application that applies Machine Learning models to defend against epidemic-style cybersecurity threats such as **XSS attacks, SQL Injection, and Malicious URLs**. --- ## Features - 🛡️ **XSS Detection** — Uses a deep learning model (`xss_model.h5`) - 🔍 **SQL Injection Detection** — Uses trained ML model

Transformer 기반 HEAT 악성 URL 탐지 시스템