Anomaly detection

Developing synthetic data for anomaly detection

Professor Carsten Maple

Project description

A 2021 Gartner Report predicted that by 2024, 60% of the data used for the development of AI and analytics projects will be synthetically generated. However, creating synthetic data remains a non-trivial challenge. For example, recent work has shown that synthetic data, when generated using real data as an initial seed, may release information about the seed data. Other techniques to protect privacy, include differential privacy, a technique employed by all major tech firms - Google, Facebook, Apple, Amazon, Microsoft - as well as many others.

This project will consider a federated data set and Run learning experiments on the set as is; Run learning experiments on the set with privacy applied; Centralise all the data, and run learning experiments; Create synthetic data from the centralised data, and run learning experiments; Create synthetic data at the endpoints, centralise the synthetic data, and run learning experiments.

Working with our leading cybersecurity team, the findings from this internship will help to underpin teaching practice within the WMG cybersecurity programmes, helping to support the fast-paced nature of research-led teaching practice in cybersecurity.

Duties and responsibilities

Perform research into published work
Summarise findings in a report
Present the findings to stakeholders

Required skills

Good knowledge of machine learning concepts and techniques
Good knowledge of Python
Clear written and verbal communication skills

Acquired skills

Experience of performing literature review
Experience of distilling information into key findings
Experimentation and communication of results to stakeholders
Engagement with stakeholder

Apply for this project

Use the form below to apply for this project.

You must be signed in to submit your application and to receive a confirmation email.

This form is closed and is no longer accepting any submissions. Thank you for your time.