KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection
Yuexin Li, Mei Lin Lock, Tri Cao, Nay Oo, Hoon Wei Lim, Bryan Hooi
33rd USENIX Security Symposium · Day 1 · USENIX Security '24
Phishing attacks remain a pervasive and costly threat, leading to significant financial losses globally. Despite advancements in detection mechanisms, a critical gap persists in effectively identifying sophisticated phishing campaigns that target a vast array of brands or employ subtle evasion tactics. The talk "KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection" introduces a novel, comprehensive approach to significantly bolster the accuracy and coverage of phishing detection systems. Presented by Yuexin Li from the National University of Singapore and their collaborators, this work addresses the inherent limitations of existing reference-based detectors, which often struggle with limited brand knowledge and an inability to detect phishing pages that do not overtly display logos.
AI review
This research presents KnowPhish, a robust system integrating a large-scale, multimodal brand knowledge base with LLMs to significantly enhance reference-based phishing detection. It addresses critical limitations by expanding brand coverage to over 20,000 targets and effectively detecting logo-less phishing pages, offering crucial advancements in combating sophisticated attacks. This is a practical, impactful step forward in a critical defense area.