Anomaly Detection Applied to Coordination Analyses

• Grant number: 25/12379-1
• Support Opportunities: Scholarships abroad - Research Internship - Scientific Initiation
• Start date: March 31, 2026
• End date: July 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Diego Raphael Amancio
• Grantee: Antônio Carlos de Almeida Micheli Neto
• Supervisor: Emilio Ferrara
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Institution abroad: University of Southern California (USC), United States
• Associated to the scholarship: 24/17173-0 - Detection of Coordination Networks in Social Media during the 2022 Brazilian Elections, BP.IC

Abstract

In the 21st century, social media has become a central arena for public discourse, heavily influenced by Information Operations (IO), where coordinated, inauthentic groups manipulate narratives; despite the growing sophistication of these malicious campaigns, often powered by advanced machine learning and deep learning, the use of these same technologies for detection and defense remains disproportionately low, a gap this research aims to address by exploring graph anomaly detection as a novel approach to identify such information campaigns. (AU)