Skip to content

๐Ÿš€ End-to-end Big Data Analytics pipeline using ELK Stack (Dockerized) and Isolation Forest algorithm to detect anomalies in 1.3GB+ Web Server Logs.

Notifications You must be signed in to change notification settings

khalifaalhasan/LogSentinel

Repository files navigation

๐Ÿ›ก๏ธ LogSentinel-ELK: Web Traffic Anomaly Detection

ELK Stack Python Docker License

LogSentinel-ELK is a Big Data project designed to process, analyze, and detect anomalies in massive web server logs (>1.3 GB). By leveraging the power of ELK Stack (Elasticsearch, Logstash, Kibana) for data engineering and Unsupervised Machine Learning (Isolation Forest) for security analysis, this system can identify potential cyber threats such as DDoS attacks, brute force attempts, and data exfiltration.


๐Ÿ“Š Project Architecture

The pipeline consists of three main stages:

  1. Ingestion & ETL: Parsing raw TSV logs using Logstash (Grok/CSV filters) and normalizing timestamps.
  2. Storage & Visualization: Indexing 13M+ records in Elasticsearch and visualizing traffic patterns in Kibana.
  3. Advanced Analysis: Extracting features using Python and applying Isolation Forest to detect outliers.

[Image of ELK Stack Architecture] (You can upload your architecture diagram here)


๐Ÿ› ๏ธ Tech Stack

  • Infrastructure: Docker & Docker Compose
  • ETL Pipeline: Logstash 7.17
  • Database: Elasticsearch 7.17 (Single Node Cluster)
  • Visualization: Kibana 7.17
  • Machine Learning: Python (Pandas, Scikit-Learn, Matplotlib)
  • Dataset: NASA HTTP Server Log (Augmented to 1.3 GB / ~13 Million Hits)

๐Ÿš€ Getting Started

Prerequisites

  • Docker Desktop (Engine running)
  • Python 3.x
  • Git

1. Clone the Repository

git clone [https://github.com/khalifaalhasan/LogSentinel-ELK.git](https://github.com/khalifaalhasan/LogSentinel-ELK.git)
cd LogSentinel-ELK

About

๐Ÿš€ End-to-end Big Data Analytics pipeline using ELK Stack (Dockerized) and Isolation Forest algorithm to detect anomalies in 1.3GB+ Web Server Logs.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages