# EncryptedTrafficClassification

**Repository Path**: yue123161/EncryptedTrafficClassification

## Basic Information

- **Project Name**: EncryptedTrafficClassification
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2023-10-29
- **Last Updated**: 2023-10-29

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

## Encrypted Traffic Classification
A simple DNN-based encrypted traffic classifier.  
The model takes the first 100 bytes of a packet(starting from eth header, pad with 0s if packet length is <100), which is classified into QQ/WeChat/HTTPS. Packets are captured with `scapy` on the fly.  
On our dataset, the model is trained to have an accuracy of 92.1%.