Detection and Investigation of Email Exfiltration Events in Sun Life Cybersecurity Data

The overall goal of this work is to use interactive machine learning to enhance current methods for detecting data exfiltration. This includes more efficient and scalable approaches for detecting and screening potentially malicious activities.
The proposal work will proceed in two stages, first focusing on the work of the corporate data analysis team in screening for suspicious activities, and then working with the corporate investigative team to make identification of actual data exfiltration activity more efficient.
In addition to strengthening Sun Life cybersecurity capability, the research should also lead to scientific publications on how to implement interactive machine learning in the context of defending against data exfiltration threats.

Faculty Supervisor:

Mark Chignell

Student:

Partner:

Sun Life Financial

Discipline:

Engineering

Sector:

Finance and Insurance

University:

University of Toronto

Program: