The agenda for the seminar this week is listed below:

Title: A Proactive System Detecting Youtube Videos Targeted by Online Communities Coordinated Hate Attacks.


Over the years, the Web has shrunk the world, allowing individuals to share viewpoints with many more people than they are able to in real life. At the same time, however, it has also enabled anti-social and toxic behavior to occur at an unprecedented scale. Video sharing platforms like YouTube receive uploads from millions of users, covering a wide variety of topics and allowing others to comment and interact in response. Unfortunately, these communities are periodically plagued with aggression and hate attacks. In particular, recent work has shown how these attacks often take place as a result of “raids”, i.e., organized efforts coordinated by ad-hoc mobs from third-party communities. Despite the increasing relevance of this phenomenon, online services often lack effective countermeasures to mitigate it. Unlike well-studied problems like spam and phishing, coordinated aggressive behavior both targets and is perpetrated by humans, making defense mechanisms that look for automated activity unsuitable. Therefore, the de-facto solution is to re-actively rely on user reports and human reviews. In this paper, we propose an automated solution to identify videos that are likely to be targeted by coordinated harassers. First, we characterize and model YouTube videos along with several axes (metadata, audio transcripts, thumbnails) based on a ground truth dataset of raid victims. Then, we use an ensemble of classifiers to determine the likelihood that a video will be raided with high Accuracy (AUC up to 94%). Overall, our work represents an important first step toward providing video platforms like YouTube with proactive systems geared to detect and mitigate coordinated hate attacks.


Enrico Mariconti is a PhD student of the UCL Department of Security and Crime Science. He is part of the SECReT DTC and during his PhD he focused mainly on Malware detection. Part of his research is also studying social network related issues and the use of machine learning techniques and statistical tests to measure and evaluate these issues. His studies at UCL started in 2014 under the supervision of Dr. Gianluca Stringhini and Dr. Gordon Ross. He has a background in Telecommunication Engineering (BSc and MSc at Università degli Studi di Genova) and, as part of the DTC, an MRes in Security Science

Venue: Francis Bancroft 2.41

Time and Date: 2 to 3 PM, Wednesday, 30/05/18.

Please keep the dates on your calendar

Any comments, advice would be appreciated.

Seminar: Enrico Mariconti