Posts

Classifying E-petitions using BERT

Image
Introduction: The project focuses on training a BERT-based model for text classification specific to Japanese e-petitions. The goal is to classify petitions into 6 classes predefined by the data source. This type of classification allows for assisting organizations in their understanding of online petitions, which can be crucial for various societal causes in Japan. Data Acquisition To begin the project, data for training the BERT model was required, and since no Japanese data was available at the time, I decided to gather it myself. The data was collected through web scraping of the change.org/ja website and the Japanese regions' change.org.  The Python code leverages Selenium, a web automation tool, to interact with the webpage, extract relevant data, and save it for further processing. As the default browser on the device was Brave, the scraper was also designed to use the Brave browser as the web driver. While scraping, the scraper implements a looped scrolling mechanism to loa...

SOC Automation Project - Wazuh, TheHive, Shuffle

Image
This project consists of building a SOC (Security Operations Center) automation lab from scratch, aimed at gaining hands-on experience in the field. The project involves setting up various tools such as Wazuh (SIEM and XDR), TheHive (for case management), and Shuffle (for SOAR capabilities). The project includes 5 different parts: Part 1: Creating a logical diagram to visualize the lab and project. Part 2: Installing necessary components and setting up the lab in the cloud and virtual machines (VM). Part 3: Configuring servers and endpoints for seamless communication with each other. Part 4: Generating telemetry related to Mimikatz to trigger alerts. Part 5: Setting up SOAR, integrating all tools, and automating responses and alerts. Part 1:  In the first part of the project, the focus is on creating a logical diagram to visualize the lab setup, which would help to understand data flow and identify necessary components. I used a free tool called draw.io to build this diagram, by co...

Home Network Simulation in Cisco Packet Tracer

Image
 1. Objective: Utilizing Cisco Packet Tracer, I sought to design and build a simulated home network system suitable for high network demanding users, such as remote workers and professionals. The design is made to ensure the safety of the users, by integrating modern cybersecurity standards. 2. Network Topology Overview in Cisco Packet Tracer: Above is a topology diagram, built through Cisco Packet Tracer, which illustrates the network flow starting from the Cloud PT, via a 2901 router, through a 2960 24TT switch, to a WRT300 wireless router, which finally connects multiple end-point devices. The green triangles between the devices represents a successful connection.                                         Above is the physical simulation of the networking. A. Cloud PT (Packet Tracer Cloud  - The Cloud PT is a generic device that represents external networks/...