Hijack Vertical Federated Learning Models As One Party
This addresses a critical security gap in VFL for practitioners, though it is incremental as it builds on existing VFL frameworks.
The paper identifies a security vulnerability in vertical federated learning (VFL) models, where an attacker can hijack the model as a single party, compromising its integrity without prior knowledge.
Vertical federated learning (VFL) is an emerging paradigm that enables collaborators to build machine learning models together in a distributed fashion. In general, these parties have a group of users in common but own different features. Existing VFL frameworks use cryptographic techniques to provide data privacy and security guarantees, leading to a line of works studying computing efficiency and fast implementation. However, the security of VFL's model remains underexplored.