PHISHREV: A Hybrid Machine Learning and Post-Hoc Non-monotonic Reasoning Framework for Context-Aware Phishing Website Classification

TL;DR

This paper introduces PHISHREV, a hybrid framework combining machine learning and non-monotonic reasoning to improve context-aware phishing website classification, enhancing decision consistency and adaptability.

Contribution

It presents a novel hybrid approach integrating classifiers with Answer Set Programming for context-aware, post-hoc decision refinement without retraining models.

Findings

Reasoning module modifies 5.08% of classifier outputs.

Improved decision consistency in phishing detection.

Incorporating new domain knowledge takes O(n) time.

Abstract

Phishing detection systems are predominantly rely on statistical machine learning models, which often lack contextual reasoning and are vulnerable to adversarial manipulation. In this work, we propose a hybrid framework that integrates machine learning classifiers with non-monotonic reasoning using Answer Set Programming (ASP) to enable context-aware decision refinement. The proposed post-hoc reasoning layer incorporates expert knowledge to revise classifier predictions through formal belief revisions. Experimental results indicate that the reasoning module modifies 5.08\% of classifier outputs, leading to improved decision consistency. A key advantage is that new domain knowledge can be incorporated into the reasoning layer in $\mathcal{O}(n)$ time, eliminating the need for model retraining.