Data synthesis Research Project

This is the home page of data synthesis project from CNLAB-University of Victoria.

GETTING STARTED

• Installation
  • Requirements
  • Install from Docker Image
  • Install from Custom Environment
• Pre-requisites
• Install Dependencies
  • Install smf
• Post-installation
• Quickstart: BERT Pre-trained Model Fine-tuning on WAF Dataset
  • Introduction
  • Dataset Introduction
  • Step 1: Prepare the Dataset
  • Step 2: Download the Base Model
  • Step 3: Fine-tune the Model
  • Step 4: Evaluate the Model
  • References
• codestyle
• Project Overview
• Design Principles
• Functional Architecture
• Core Modules
  • Configuration Module
  • Data Cleaning Module
  • Data Preparation Module
  • Model Training Module
  • Logging Module
  • Evaluation Module
  • Documentation Module
  • Testing Module
• Datasets
  • Overview
  • Structure
  • Data Sources
  • Processing
  • Dataset-specific Information
• Style-controlled Phishing Email Data Generation with Score Entropy Discrete Diffusion
  • Methodology
  • Workflow of style-controlled diffusion for phishing email generation
  • References
• Diffusers Library for Quickly Building and Deploying Diffusion Models
  • Unique Features