Peak-controlled logits poisoning attack in federated distillation

Abstract Federated Distillation (FD) is an innovative distributed machine learning paradigm that enables efficient and flexible cross-device knowledge transfer through knowledge distillation, without the need to upload large-scale model parameters to a central server. Although FD has attracted incre...

Descripció completa

Dades bibliogràfiques

Autors principals:	Yuhan Tang, Zhiyuan Wu, Bo Gao, Tian Wen, Yuwei Wang, Sheng Sun
Format:	Artigo
Idioma:	Inglês
Publicat:	Springer 2025-10-01
Col·lecció:	Discover Computing
Matèries:	Federated learning Knowledge distillation Knowledge transfer Poisoning attack Misleading attack
Accés en línia:	https://doi.org/10.1007/s10791-025-09742-8
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!