Realistic Synthetic Dataset Generator

The goal of the project is to assess the viability of current synthetic data generation systems. If the generated synthetic data is accurate enough without providing sensitive details it can be used to train machine learning models without needing to share sensitive information. The particular application of this project is to computer logs which can contain sensitive information about the computer systems themselves or the individuals using them. If synthetic data can be generated accurately, it could be used to generate more accurate anomaly detectors Arctic Wolf may be able to implement in their monitoring suites without needing to put the data subject’s privacy at risk.

Faculty Supervisor:

Charlie Obimbo

Student:

Partner:

Arctic Wolf Networks

Discipline:

Computer science

Sector:

Information and cultural industries; Professional, scientific and technical services

University:

University of Guelph

Program: