QR code

Untargeted poisoning attack based on fake clients and its defense in federated learning

Abstract Untargeted poisoning attacks pose a serious threat to federated learning. However, existing untargeted poisoning attacks have limitations. Most attacks assume that the adversary can control a large number of real clients, which is difficult to achieve in practice. Although the poisoning att...

Volledige beschrijving

Bewaard in:
Hoofdauteurs: Caimei Wang, Kangjian Xu, An He, Zhipeng Sun, Jianzhong Pan, Yudong Ren
Formaat: Artigo
Taal:Inglês
Gepubliceerd in: SpringerOpen 2025-12-01
Reeks:Cybersecurity
Onderwerpen:
Security
Machine learning
Federated learning
Poisoning attack
Online toegang:https://doi.org/10.1186/s42400-025-00389-y
Tags: Voeg label toe
Geen labels, Wees de eerste die dit record labelt!

Gelijkaardige items