About the Project
While the internet provides an excellent platform for communication it also offers the opportunity for malicious behaviour. These undesirable behaviours can include cyberbullying, spamming, or disinformation (‘fake news’). These malicious actors can range from something as simple as an ‘internet troll’, to hacking groups or state sponsored actors [i].
Social honeypots [ii] have been used as a means of capturing and characterising social media spammers to better understand their interactions with the services. Traditionally, this approach involves creating a number of social media profiles to attract specific malicious actors. This data is then analysed to better understand the attributes and behaviours of these accounts.
This PhD project will extend this approach to develop a range of interactive social honeypots by using automated bots (a honeypot-bot) to actively engage with trolls, fake news and automated accounts.
The project will aim to design and create a number of bots that can be deployed to engage with other malicious or automated actors. Initially, the work will focus on developing Twitter-bots, however, this can be expanded to provide a generic approach to deploying these ‘honeypot-bots’ across a range of platforms.
The research will require the analysis of the behaviours of real users, malicious actors and automated accounts. This will require a number of experiments to determine which characteristics of a bot make it more attractive to certain groups (e.g. the avatar or language used).
The research will cover a broad range of topics in order to create convincing bots that can attract automated or malicious accounts as well as being realistic enough to avoid being identified as spam.
This project will use a variety of skills including:
• Programming
• Natural Language Processing (NLP)
• Linguistic analysis [iii]
• Data analytics
• Machine learning
For any enquiries please contact the supervisor ([Email Address Removed]).
For more information on the supervisor for this project, please go here: https://www.uea.ac.uk/computing/people/profile/o-buckley
Type of programme: PhD
Project start date: October 2019
Mode of study: Full time
Entry requirements: Acceptable first degree - Computer Science (or related subject). The standard minimum entry requirement is 2:1.
Funding Notes
This PhD project is in a Faculty of Science competition for funded studentships. These studentships are funded for 3 years and comprise home/EU fees, an annual stipend of £14,777 and £1,000 per annum to support research training. Overseas applicants may apply but they are required to fund the difference between home/EU and overseas tuition fees (which for 2018-19 are detailed on the University’s fees pages at https://portal.uea.ac.uk/planningoffice/tuition-fees . Please note tuition fees are subject to an annual increase).
References
[1] Zannettou, S., Caulfield, T., De Cristofaro, E., Sirivianos, M., Stringhini, G. and Blackburn, J., 2018. Disinformation Warfare: Understanding State-Sponsored Trolls on Twitter and Their Influence on the Web. arXiv preprint arXiv:1801.09288.
[2] Webb, S., Caverlee, J. and Pu, C., 2008, August. Social Honeypots: Making Friends With A Spammer Near You. In CEAS (pp. 1-10).
[3] Lee, K., Caverlee, J. and Webb, S., 2010, July. Uncovering social spammers: social honeypots+ machine learning. In Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval (pp. 435-442). ACM.
[4] Elmendili, F., Maqran, N., Idrissi, Y.E.B.E. and Chaoui, H., 2018. A security approach based on honeypots: Protecting Online Social network from malicious profiles. arXiv preprint arXiv:1804.09988.
[5] Wright J. and Anise O., 2018. Don’t @ Me: Hunting Twitter Bots at Scale. https://duo.com/assets/pdf/Duo-Labs-Dont-At-Me-Twitter-Bots.pdf
[6] The New York Times, 2018. Battling Fake Accounts, Twitter to Slash Millions of Followers. https://www.nytimes.com/2018/07/11/technology/twitter-fake-followers.html