Machine Learning Based Encrypted Traffic Analysis

Accurate network traffic identification would assist network operations and management teams effectively on many different network tasks such as managing bandwidth and ensuring security. The demand for network management methods that optimize network performance and provide quality of service guarantees has increased substantially in recent years. As new social networking and voice over internet protocol (VoIP) applications such as Facebook and WeChat have dramatically grown in popularity over the past several years, they now constitute a significant share of the total traffic on the Internet. Therefore, identification of such network traffic plays an important role in many areas such as network management, traffic shaping, cyber security and so on. In this research, we aim to investigate how encrypted social media and VoIP traffic could be accurately and robustly identified using a machine learning based approach in network traffic data.

Faculty Supervisor:

Nur Zincir-Heywood

Student:

Ali Safari Khatouni

Partner:

Solana Networks

Discipline:

Computer science

Sector:

Information and communications technologies

University:

Program: