cic-ids-2017

Download UNSW-NB15 and CIC-IDS2017 Datasets for Network Intrusion Detection (NIDS)

En este proyecto se evalúan y comparan diferentes técnicas de aprendizaje automático para la detección de intrusiones en red.

A network Intrusion Detection System (IDS) based on Self-Organizing Neural Networks (SOINN).

Network-Based Intrusion Detection using Graph Features - A Complex Networks course project exploring graph construction from network flows, graph-theoretic features extraction, and ML/GNN-based intrusion detection using datasets such as CIC-IDS-2017 and Kaggle.

Enhancing NIDS through innovative noise techniques and data strategies.

This repository contains the submitted prototype implementation for a tenant-aware Network Intrusion Detection as a Service (NIDSaaS) pipeline.

Network Intrusion Detection System (NIDS) is a machine-learning-based system for detecting malicious network traffic in real time. The system uses the CIC-IDS2017 dataset to train supervised learning models and combines packet capture, flow generation, feature extraction, ML-based classification, alerting, and automated IP blocking into a single pi

Generative Network Traffic Augmentation via Conditional GANs for Federated Intrusion Detection in Non-IID Environments

Project for Data Literacy and AI (Semester 2 24/25) implementing PPDAC cycle and exploratory data analysis (EDA) to CIC-IDS2017 Dataset.

AI-powered Network Intrusion Detection System using Random Forest on CIC-IDS2017. Detects DDoS attacks with 99.99% accuracy. Flask API + Streamlit dashboard.

DDoS-Vision: A Deep Learning approach to network security. Converts numerical CIC-IDS2017 traffic flows into 2D grayscale images for CNN classification. Features Grad-CAM for Explainable AI (XAI) and 99% detection accuracy.

Deduplication experiment for the RF anomaly-detection branch of NIDaaS using CIC-IDS2017.

Machine learning for network intrusion detection using CIC-IDS-2017 benchmark dataset