VisualPhishNet: Zero-Day Phishing Website Detection by Visual Similarity
This addresses the threat of phishing websites for internet users, offering improved detection of unseen phishing pages, though it is incremental as it builds on similarity-based methods.
The paper tackles the problem of detecting zero-day phishing websites by visual similarity, introducing VisualPhishNet, a triplet CNN-based framework that learns website profiles and generalizes to new visual appearances, outperforming previous methods by a large margin and showing robustness against evasion attacks.
Phishing websites are still a major threat in today's Internet ecosystem. Despite numerous previous efforts, similarity-based detection methods do not offer sufficient protection for the trusted websites - in particular against unseen phishing pages. This paper contributes VisualPhishNet, a new similarity-based phishing detection framework, based on a triplet Convolutional Neural Network (CNN). VisualPhishNet learns profiles for websites in order to detect phishing websites by a similarity metric that can generalize to pages with new visual appearances. We furthermore present VisualPhish, the largest dataset to date that facilitates visual phishing detection in an ecologically valid manner. We show that our method outperforms previous visual similarity phishing detection approaches by a large margin while being robust against a range of evasion attacks.