Embedding Asymmetry as Attack Signal: Detecting and Defending Active Label Inference in Vertical Federated Learning

본문 미리보기

arXiv:2610.14194v1 Announce Type: new Abstract: Vertical federated learning lets organizations train a shared model over features they hold separately, while one party keeps the labels private. The active label inference attack of Fu et al. [12] breaks this: a feature-holding party runs a modified optimizer, MaliciousSGD, that forces class structure into its embeddings and then recovers the labels with semi-supervised learning. Defenses that perturb the shared gradient fail, because the attack