User-Centered Phishing Detection through Personalized Edge Computing
Sanchari Das, DongInn Kim, Jacob Abbott, L. Jean Camp · 2024
Ensuring user-centered phishing detection is a significant challenge due to the difficulty in distinguishing threats. To address this, we propose a personalized tool - Holistic User-Centered Identification of Threats at the Edge (HUCITE). Our system utilizes probabilistic logic to provide real-time risk estimates for local machines and employs simple cartoons as a user interface. Our approach focuses on identifying anomalies in a single machine and user browsing history for the generation of a personalized green list and global threat information for a shared red list. This approach enables blocking and identification of phishing websites, potentially malicious scripts, unfamiliar domains, and previously unencountered certificate authorities. By creating a zone of safety for a specific user and identifying departures from that zone, our approach addresses the limitations of traditional anomaly detection techniques. We present the underlying architecture and approach to local risk identification, reporting on an in-lab experiment involving 45 participants to test the effectiveness of our system in various stress conditions affecting users' phishing perception.