unsw-nb15-dataset

A Python framework for N-agent collective learning using Tsetlin Machines and synthetic data sharing, supporting zero-shot sensor onboarding and LLM-driven feature extraction.

Federated Learning IDS — Privacy Attack Analysis

Real-time Intrusion Detection System using Signature-Based Detection, DNS Threat Intelligence, and Machine Learning Attack Classification.

ML-powered network anomaly detection system for identifying anomalous network traffic using Flask and Scikit-learn.

Machine Learning based Network Traffic Forensics research project using the UNSW-NB15 dataset for cyber crime investigation and intrusion detection. This B.Tech CSE (AI & ML) final semester research paper 2022 - 2026 focuses on supervised Machine Learning models including Decision Tree, Random Forest, and Linear SVM .

Network traffic classification using Machine Learning

A practical coursework-style project from my Master's studies in Big Data Analytics (at University of East London), showcasing hands-on use of big data tools and techniques on a real-world cyber-security dataset.

Machine learning analysis of the UNSW-NB15 cybersecurity dataset using R with logistic regression and random forest models.

Détection de cyberattaques par Temporal Graph Network (TGN) sur graphe dynamique de communication IP — PyTorch Geometric, jeu de données UNSW-NB15

End-to-end ML intrusion detection system on UNSW-NB15 with Random Forest, FastAPI, Docker and monitoring

This project utilizes Apache Hadoop, Hive, and PySpark to process and analyze the UNSW-NB15 dataset, enabling advanced query analysis, machine learning modeling, and visualization. The project demonstrates efficient data ingestion, processing, and predictive analytics for network security insights.

SOC-ready cybersecurity system for network intrusion detection using hybrid machine learning (Isolation Forest + Random Forest) with SMOTE-based imbalance handling and SOC-style security analytics on UNSW-NB15.