My research focuses on the identification and detection of emerging online fraudulent activity, and the development of AI-based solutions for early detection and mitigation of such malevolent behaviour. I have extensive experience working with large-scale, multi-platform datasets, developing analytical pipelines, and applying advanced NLP and machine learning methods. Previously, as a Postdoctoral Researcher at UCL, I worked on projects related to cybercrime, fraud analysis, and behavioural modelling of online offenders. During my time as a PhD researcher, my research focused on the characterization and detection of extremist, conspiratory-focused, and fringe communities in alternative and mainstream social networks. This work employed various quantitative and qualitative data analysis methods, statistical analysis, and Natural Language Processing and Discourse Analysis tools. Before that, as a Research Fellow at CUT, my research focused on device-centric authentication, federated identity management, the cybersafety of minors online, and the detection and characterization of inappropriate content online, while actively contributing to EU-funded projects (ReCRED and ENCASE). In addition, I had the opportunity to spend 8 months (in total) as an intern at Telefonica I+D, Barcelona, Spain. During my bachelor studies I conducted research on unmanned surface vessels, robotics, and automation (PID controlled systems).