A Modular and Adaptive System for Business Email Compromise Detection

TL;DR

CAPE is a modular, adaptive system that combines multiple machine learning models and behavioral detectors across email modalities to effectively detect Business Email Compromise attacks, with proven deployment over two years.

Contribution

The paper introduces CAPE, a novel, multi-modal BEC detection system that integrates diverse models and explainability, and demonstrates its effectiveness in a real-world environment.

Findings

Proven effectiveness of CAPE in production for over two years

CAPE's modular design enables explainability and continuous adaptation

Integration of multiple models improves detection accuracy

Abstract

The growing sophistication of Business Email Compromise (BEC) and spear phishing attacks poses significant challenges to organizations worldwide. The techniques featured in traditional spam and phishing detection are insufficient due to the tailored nature of modern BEC attacks as they often blend in with the regular benign traffic. Recent advances in machine learning, particularly in Natural Language Understanding (NLU), offer a promising avenue for combating such attacks but in a practical system, due to limitations such as data availability, operational costs, verdict explainability requirements or a need to robustly evolve the system, it is essential to combine multiple approaches together. We present CAPE, a comprehensive and efficient system for BEC detection that has been proven in a production environment for a period of over two years. Rather than being a single model, CAPE is a system that combines independent ML models and algorithms detecting BEC-related behaviors across various email modalities such as text, images, metadata and the email's communication context. This decomposition makes CAPE's verdicts naturally explainable. In the paper, we describe the design principles and constraints behind its architecture, as well as the challenges of model design, evaluation and adapting the system continuously through a Bayesian approach that combines limited data with domain knowledge. Furthermore, we elaborate on several specific behavioral detectors, such as those based on Transformer neural architectures.