A Scalable Vertical Federated Learning Framework for Analytics in the Cybersecurity Domain

This paper presents a Scalable Vertical Federated Learning (SVFL) framework designed to address the task of clas-sification in the cybersecurity domain. SVFL combines vertical federated learning (VFL) with scalable computing architectures, enabling efficient analysis of large-scale and sensitive cybersecu-rity datasets while maintaining data confidentiality. The frame-work is adaptable to diverse use cases, scalable for increasing data volumes, and robust in dynamic and adversarial environments. In addition, adopting the VFL paradigm ensures a good trade-off between privacy and performance. Experimental results demon-strate the framework's effectiveness in enhancing collaborative threat detection and prevention, offering a promising solution for advancing cybersecurity analytics. Preliminary experiments conducted on a well-known cybersecurity dataset show that the accuracy of the systems does not degrade excessively compared to a baseline owning all the data locally.