Improving Social Bot Detection with an AML Approach


Social bots are automated accounts often involved in unethical or illegal activities. Academia has shown how these accounts evolve over time, becoming increasingly smart at hiding their true nature by disguising themselves as genuine accounts. If they evade, bots hunters adapt their solutions to find them: the cat and mouse game. Inspired by adversarial machine learning and computer security, in this talk we'll see an adversarial and proactive approach to social bot detection. A practical example of the application of this approach will be presented introducing the Digital DNA framework, proposed to study groups' behaviors in social networks and for bot detection.

21/11/2019

Time: 10:00
Venue: Dipartimento di Informatica, Via Salaria 113, Third Floor, Seminari Lecture Room
Speaker: Angelo Spognardi

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma