Cyri leverages Large Language Models to create an interactive security assistant that supports users in identifying and responding to phishing emails through conversational analysis.

• Analyzes emails for semantic phishing indicators like urgency and threatening consequences
• Combines established security features with novel detection methods
• Designed for integration with email clients to provide real-time support
• Educates users about phishing tactics while providing protection

This research matters because it represents a shift from traditional automated filters to AI-assisted human judgment, potentially reducing successful phishing attacks in organizational settings while building user security awareness.

Original Paper: Cyri: A Conversational AI-based Assistant for Supporting the Human User in Detecting and Responding to Phishing Attacks