Use this URL to cite or link to this record in EThOS:
Title: On combating online radicalisation : a framework for cybercrime investigations
Author: Nouh, Mariam A.
ISNI:       0000 0004 9355 1708
Awarding Body: University of Oxford
Current Institution: University of Oxford
Date of Award: 2019
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Restricted access.
Access from Institution:
“The Internet is the crime scene of the 21st century.” The complexity of cybercrimes is constantly increasing with advanced tools, attack vectors, and Modus Operandi adopted by offenders every day. Criminals have easy access to advanced technical abilities that they need to carry their attacks, using what is called crime-as-a-service, from the dark web and online black markets. Similarly, the nature of cybercrimes has generated multitudes of data introduced by the “cyber” aspect of these crimes, which makes the process of identifying evidence similar to searching for a needle in a haystack. To aid law enforcement to better detect, analyse, and understand the threat landscape posed by cyber-criminals, research into the area of cybercrime intelligence has flourished. Law enforcement faces numerous challenges when policing cybercrimes. The methods and processes they use when dealing with traditional crimes do not necessarily apply in the cyber world. Additionally, criminals are usually technologically-aware and one step ahead of the police. Furthermore, current tools created to support law enforcement to better police cybercrimes more often conflict with how they are used to operate, and are too complex, thus making them difficult to adopt. In this thesis, we aim to design and develop a cybercrime intelligence framework for law enforcement that provides decision support to detect and analyse the behaviour of cyber-criminals. To do so, we need to better understand the cyber-criminal ecosystem, as well as understand the current capabilities of law enforcement agencies, and the challenges they face when policing cybercrimes. We achieve this through semi-structured interviews conducted with professionals and law enforcement agents investigating cybercrimes. From there, we define a framework to aid them in addressing some of the challenges they face. Moreover, the cybercrime landscape varies considerably in regards to the type of crime and what they target. Some crimes target computers and systems while others target the human. As there has been considerable research focusing on analysing cybercrimes that target systems such as (Malware, Hacking, DDOS), the focus on the crimes that target the human ( e.g., cyber-bullying, online radicalisation) has recently become more evident. In this research, we focus on the area of online radicalisation and utilise our framework to better understand the properties of radical propaganda and develop methods to defend against its spread. We focus on the ISIS group aiming to identify measures to automatically detect radical content and activities in social media. We identify several signals, including textual, psychological and behavioural, that together allow for the identification of radical messages, using methods such as natural language processing, social network analysis, and machine learning. Our findings can be utilised as signals for detecting online radicalisation activities by law enforcement and social media platforms to help keep the online world safe.
Supervisor: Goldsmith, Michael ; Nurse, Jason Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: Computer Science ; Cyber Security