Robust Phishing Detection Against Adversaries

Abstract

Phishing websites have grown more recently than ever, and they become more intelligent, even against well-designed phishing detection techniques. Formerly, we have proposed in the literature a state-of-the-art URL-exclusive phishing detection solution based on Convolutional Neural Network (CNN) model, which we referred as PUCNN model. Phishing detection is adversarial as the phisher may attempt to avoid the detection. This adversarial nature makes standard evaluations less useful in predicting model performance in such adversarial situations. We aim to improve PUCNN by addressing the adversarial nature of phishing detection with a restricted adversarial scenario, as PUCNN has shown that an unrestricted attacker dominates. To evaluate this adversarial scenario, we present a parameterized text-based mutation strategy used for generating adversarial samples. These parameters tune the attacker’s restrictions. We have focused on text-based mutation due to our focus on URL-exclusive models. The PUCNN model generally showed robustness and performed well when the parameters were low, which indicates a more restricted attacker.