Austin Hounsel will present his General Exam "Disinfotron: Early and Progressive Detection of Online Disinformation" on Thursday, May 9th at 7:30am in CS 402.

Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below.

Committee: Nick Feamster, Jonathan Mayer, and Kyle Jamieson

Title: Disinfotron: Early and Progressive Detection of Online Disinformation

Abstract: Online disinformation is a serious and growing threat to the integrity of public discourse, democratic governance, and commerce. Disinformation is not new, but the Internet has made it cheaper, easier, and more effective. Although major online platforms are deploying systems to counter disinformation, existing approaches largely rely on user moderation and manual analysis. The scalability challenges and delays associated with these approaches significantly undermine their efficacy; by the time a platform takes action, disinformation has already spread and achieved its intended effect.

This paper presents a new approach to detecting disinformation: Disinfotron, an automated early warning system that progressively detects new disinformation campaigns at key stages of the deployment lifecycle. Drawing inspiration from previous work that detects malware distribution, phishing, and scams from network-level and application-level features, we demonstrate the feasibility of detecting disinformation campaigns before they can spread, and in some cases before they can even launch. Disinfotron uses domain, certificate, and hosting features to classify websites as either disinformation, news, or lacking news content. Our results demonstrate that Disinfotron is fast, accurate, and scalable.

Reading list:

Textbook:

Kurose, J. F., & Ross, K. W. (2016). Computer networking: A top-down approach. Boston, MA: Pearson.

Papers:

Allcott, H., & Gentzkow, M. (2017). Social media and fake news in the 2016 election. Journal of economic perspectives, 31(2), 211-36.

Pérez-Rosas, V., Kleinberg, B., Lefevre, A., & Mihalcea, R. (2018, August). Automatic Detection of Fake News. In Proceedings of the 27th International Conference on Computational Linguistics (pp. 3391-3401).
Baly, R., Karadzhov, G., Alexandrov, D., Glass, J., & Nakov, P. (2018). Predicting factuality of reporting and bias of news media sources. arXiv preprint arXiv:1810.01765.

Ratkiewicz, J., Conover, M. D., Meiss, M., Gonçalves, B., Flammini, A., & Menczer, F. M. (2011, July). Detecting and tracking political abuse in social media. In Fifth international AAAI conference on weblogs and social media.
Ma, J., Saul, L. K., Savage, S., & Voelker, G. M. (2009, June). Identifying suspicious URLs: an application of large-scale online learning. In Proceedings of the 26th annual international conference on machine learning (pp. 681-688). ACM.
Ramachandran, A., & Feamster, N. (2006, September). Understanding the network-level behavior of spammers. In ACM SIGCOMM Computer Communication Review (Vol. 36, No. 4, pp. 291-302). ACM.
Hao, S., Kantchelian, A., Miller, B., Paxson, V., & Feamster, N. (2016, October). PREDATOR: proactive recognition and elimination of domain abuse at time-of-registration. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (pp. 1568-1579). ACM.
Hao, S., Syed, N. A., Feamster, N., Gray, A. G., & Krasser, S. (2009, August). Detecting Spammers with SNARE: Spatio-temporal Network-level Automatic Reputation Engine. In USENIX security symposium (Vol. 9).
Thomas, K., Grier, C., Ma, J., Paxson, V., & Song, D. (2011, May). Design and evaluation of a real-time url spam filtering service. In 2011 IEEE symposium on security and privacy (pp. 447-462). IEEE.
Grier, C., Thomas, K., Paxson, V., & Zhang, M. (2010, October). @ spam: the underground on 140 characters or less. In Proceedings of the 17th ACM conference on Computer and communications security (pp. 27-37). ACM.