Federated Learning for Anomaly Detection in Open RAN (O-RAN)

About the Project

Applications are invited for a self-funded, 3 year full-time or 6-year part-time PhD project.

The PhD will be based in the School of Computing and will be supervised by Dr. Rahim Taheri and Dr. Mo Adda.

The work on this project will:

• Investigate Federated Learning (FL) techniques for distributed anomaly detection in O-RAN networks.
• Design secure aggregation mechanisms resilient to adversarial and poisoning attacks in O-RAN networks.
• Evaluate privacy-preserving training strategies using telemetry and log data from edge nodes and RAN controllers.
• Develop real-time, lightweight models that can be deployed in near-RT RIC environments.

Project description

The Open Radio Access Network (O-RAN) framework introduces flexibility and openness to 5G and future 6G systems, enabling modularity and interoperability across different vendors. However, this shift also exposes critical infrastructure to new vulnerabilities and attack surfaces.

This project aims to develop a Federated Learning-based security solution for O-RAN systems to detect anomalies and cyber threats in a distributed, privacy-conscious manner. Instead of relying on centralized intrusion detection systems, the project will explore how machine learning models can be collaboratively trained across distributed RAN components—such as base stations and edge servers—without transferring raw data.

Key research objectives include:

• Designing FL protocols tailored for heterogeneous edge nodes in the RAN.
• Developing lightweight, communication-efficient models suitable for deployment in real-time environments.
• Investigating defense strategies against model poisoning, data manipulation, and adversarial attacks in FL scenarios.
• Evaluating system performance using telecom simulators or emulators like OpenAirInterface or srsRAN.

General admissions criteria

A good first degree (minimum upper second class or equivalent) or a Master’s in Computer Science, Cybersecurity, Telecommunications, or a related area. Exceptional candidates with relevant industry experience may also be considered.

English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.

Specific candidate requirements

• Experience with machine learning and Python programming.
• Understanding of Federated Learning and distributed training frameworks.
• Background knowledge of 5G/6G network architecture and O-RAN is desirable.
• Familiarity with telecom simulation tools is a plus.

How to Apply

We’d encourage you to contact Dr Rahim Taheri (rahim.taheri@port.ac.uk) to discuss your interest before you apply, quoting the project code.

When you are ready to apply, please follow the 'Apply now' link on the Computing PhD subject area page and select the link for the relevant intake. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our ‘How to Apply’ page offers further guidance on the PhD application process.

When applying please quote project code: CMP10181026