Research Area: Digital Forensics
This thesis examines the application of machine learning to policing. First, it identifies and maps online criminality, forming a framework in order to allow software to learn criminal behavior. Then, it demonstrates automated detection and classification of child exploitation imagery, via open source software capable of running on low-end hardware. This capability represents a major leap in the investigation and combating of online radicalization and trade in child exploitation materials.
To paraphrase a broad topic, we define Digital Forensics (DF) as the identification,evaluation and presentation of data from electronic devices for the primary purpose of presentation in court. As a law enforcement field, it has evolved from individuals and ad-hoc teams working on specialist matters to dedicated laboratories em-bedded within relevant agencies worldwide, largely in response to the vast quantities of electronic devices and data emerging as a result of pervasive computing. Furthermore, the significance of data as evidence has evolved in sync with that of data in general throughout business and social life worldwide. Combined, these have resulted in the field encountering near immeasurable growth in workload and importance within investigations and prosecutions globally.
Name of the Researcher: Janis Toms Dalins
Name of the Supervisor(s): Campbell Wilson
Year of Completion: 2019
University: Monash University
Thesis Link: Home Page Url
