Encrytped Traffic cyber-attack prediction model Powered By LLM(BERT)

Project Link: https://encryptedtrafficattackclassifier.streamlit.app/

Detect Threats, Secure Networks, Empower Decisions

🚀 Built With

• Python

• pandas

• NumPy

• scikit-learn

• PyTorch

• Seaborn

• Keras

• 🌐 Streamlit

• LLM used is prajjwal1\bert-tiny

---

📚 Table of Contents

• Overview
• Getting Started
  • Prerequisites
  • Installation
  • Usage
  • Testing

---

📌 Overview

EncryptedTrafficAttackClassifierLLMs is a sophisticated developer tool designed to classify cybersecurity network traffic attacks using lightweight language models. It supports security analysts in:

• Detecting malicious activity in real time
• Enhancing network observability
• Making informed security decisions

🔐 Why EncryptedTrafficAttackClassifierLLMs?

This project streamlines encrypted traffic cyber attack prediction across 9 different attack categories with a focus on security, performance, and usability. Core features include:

• ✅ Real-time Threat Detection: An interactive Streamlit interface for instant predictions and enriched flow descriptions
• ⚙️ Model Configuration & Tokenization: Leverages Tiny BERT-based models with configurable NLP pipelines
• 📦 Environment Management: Scripts to set up and deactivate isolated Python environments reliably
• 📈 Data Visualization & Logs: In-app charts and download options for logs and predictions
• 🔐 Security & Performance: Accurately identifies traffic-related attacks to proactively mitigate threats

---

Languages Used: Python (99%), Others (1%)

🛠️ Getting Started

✅ Prerequisites

Ensure the following dependencies are installed:

• Python (version 3.7 or higher)
• pip (Python package manager)

---

📥 Installation

Follow these steps to build the project from source:

1. Clone the repository:

git clone https://github.com/suchetsanjeev/EncryptedTrafficAttackClassifierLLMs

2. Navigate to the project directory:

cd EncryptedTrafficAttackClassifierLLMs

3. Install dependencies:

pip install -r requirements.txt