The model leverages the strengths of both CNNs and BiLSTM networks to effectively capture spatial and temporal patterns in network traffic data. We trained and evaluated the model using a comprehensive dataset of cyber attacks. The model achieved a high accuracy of 99%.

This repository provides comprehensive guides, configurations, rules, and practical examples for Snort, the open-source intrusion detection system (IDS). Ideal for cybersecurity professionals and enthusiasts looking to enhance their network security skills.

A comprehensive toolkit for applying Machine Learning and Data-Driven approaches to digital forensics and cyber security investigations. Features network traffic analysis, memory forensics integration with Volatility 3, and CASE-compliant data handling.

Major project for Advanced Topics in Computer Science. Using mitmproxy to automatically detect if private data has been leaked in network traffic data by certain android applications.

Plug into extended SecOps: Bring Google Cloud's analytics to your local network. tshark captures on-prem, GCP transforms to UDM. Scalable, event-driven, via Terraform.

This project is a live network monitoring dashboard that leverages tree-based machine learning algorithms to detect intrusions in real-time. The system uses Flask and Socket.IO for real-time data updates, and Chart.js for data visualization. The dashboard provides various charts to visualize network data and sends notifications for suspicious activ

Modeling Network Traffic using Recurrent Neural Networks (Long Short-Term Memory, LSTM)

A real-time, AI-augmented network monitoring tool built with Python, Dash, and Scapy. It captures live packets or analyzes .pcap files, applies ML/AI-based filtering, detects port scans, triggers email alerts, and logs incidents. The interactive web dashboard visualizes protocol usage and traffic stats, supporting advanced visual filters.

Deployment guide for CloudLens network visibility software on Google Cloud Platform

ML pipelines for cybersecurity: packet flow feature engineering, automated LightGBM tuning, HTTP malware detection

A machine learning project to detect cyberattacks in IoT healthcare networks. Utilizes PCA for dimensionality reduction, data visualization for insights, and ANN for classification. Features a FastAPI backend and Streamlit UI for inference with labeled and unlabeled datasets.

Real-time network packet capture and analysis using Moloch (Arkime), Wireshark, and Elastic Stack to detect anomalies, visualize patterns, and enhance cybersecurity.

A simple, yet powerful Python-based network anomaly detection tool that uses machine learning to analyze network traffic and detect suspicious activity. The tool integrates with the VirusTotal API to check the reputation of anomalous IP addresses.

A machine learning implementation for network traffic classification, which can be used for network intrusion detection and traffic pattern analysis.

A simulation of network traffic using synthetic network traffic for 802.11, 3G GSM, 4G LTE, and 5G NR

A network sniffer application that captures and analyzes network traffic using machine learning to detect malicious activity. Integrated with Kafka for real-time event streaming and Flask for a web interface that provides real-time alerts. Fully Dockerized for easy deployment.

Dryad: Deploying Adaptive Trees on Programmable Switches for Networking Classification (ICNP2023)

ThreatGuard is an advanced threat detection system that utilizes the CICIDS 2017 dataset for network traffic analysis and anomaly detection.