We are happy to announce that seminars of the Engineering Live Talk series are restarting. Live talks are webinars given by a member of the IFIP WG 2.7/13.4 or by an invited expert. Group members will participate in the online meetings, while the live stream on YouTube will be publicly available.
This month, the talk will be given by Francesco Greco. The talk introduces PERSEUS, a human-centered AI framework that combines explainable phishing detection, user-focused interfaces, and adaptive training to transform users from the weakest link into active defenders against phishing attacks. The talk will be given on the 22th of June, 15:00 CET.
The link to attend is the following: https://youtube.com/live/yiNnCv3BRN0?feature=share
Human-Centered Artificial Intelligence for Phishing Defense: The PERSEUS framework
Phishing is one of the most widespread and persistent cybersecurity threats, which continues to exploit human vulnerabilities despite significant technological advances in detection systems. To address the socio-technical threat posed by phishing and defend users holistically, in this talk I present PERSEUS, an integrated approach combining human factors modeling, user-centered design of explanation interfaces, XAI- and LLM-based detection methods, and adaptive training grounded in digital twins.
These aspects are usually studied in isolation and within different fields; through a Human-Centered AI approach, PERSEUS provides a methodological and technological framework to comprehensively defend users from phishing attacks. From this perspective, users are no longer treated as the weakest link to be passively protected, but as active, aware, and empowered participants in the security ecosystem.
Short Bio
Francesco Greco is currently a post-doc Research Fellow at the Department of Computer Science of the University of Bari Aldo Moro. He is a member of the Interaction, Visualization, Usability & UX (IVU) Lab, where he conducts most of his research in the field of Human-Computer Interaction (HCI) and Usable Security. He obtained his Ph.D. in February 2026, where he investigated human-centered eXplainable Artificial Intelligence (HCXAI) solutions for cybersecurity under the supervision of Prof. Giuseppe Desolda.
From October 2023 to March 2024, he was a visiting postgraduate researcher in the CYS (Cybersecurity) research group at King’s College London, UK, under the supervision of Prof. Luca Viganò. He has been a member of ACM since March 2023, ACM SIGCHI (Special Interest Group on Computer-Human Interaction) since June 2024, and ACM SIGCHI Italy since October 2022.