WO2025003839 - MECHANISM FOR DETECTING DATA AND MODEL POISONING ATTACK IN FEDERATED LEARNING
National phase entry is expected:
Publication Number
WO/2025/003839
Publication Date
02.01.2025
International Application No.
PCT/IB2024/056005
International Filing Date
19.06.2024
Title **
[English]
MECHANISM FOR DETECTING DATA AND MODEL POISONING ATTACK IN FEDERATED LEARNING
[French]
MÉCANISME DE DÉTECTION DE DONNÉES ET D'ATTAQUE PAR EMPOISONNEMENT DE MODÈLE DANS UN APPRENTISSAGE FÉDÉRÉ
Applicants **
NOKIA SOLUTIONS AND NETWORKS OY
Inventors
AGGARWAL, Chaitanya
NAIR, Divya G
MOHAMMADI, Jafar
Priority Data
202311044131
30.06.2023
IN
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
EPO
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| Translation |
|
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing, Examination, Granting | 2558 | |
| EPO | Filing, Examination, Granting | 12319 | |
| Japan | Filing, Examination, Granting | 2331 | |
| South Korea | Filing, Examination, Granting | 2360 | |
| USA | Filing, Examination, Granting | 5940 |
Total:
25,508
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Contact Us
Abstract[English]
An apparatus comprising at least one processor, and at least one memory for storing instructions that, when executed by the at least one processor, cause the apparatus at least: to obtain local model update data from each of a plurality of clients of a federated learning, FL, procedure, to determine whether at least one of the plurality of clients is a suspicious client showing a harmful behavior in the FL procedure by conducting a test with a reference dataset, if at least one suspicious client is determined, to execute an identification procedure for identifying at least one malicious client, and to perform a global model update process considering a result of a malicious client identification.[French]
L'invention concerne un appareil comprenant au moins un processeur et au moins une mémoire permettant de stocker des instructions qui, lorsqu'elles sont exécutées par ledit au moins un processeur, amènent l'appareil au moins : à obtenir des données de mise à jour de modèle locales de la part de chacun d'une pluralité de clients d'une procédure d'apprentissage fédéré, FL, pour déterminer si au moins l'un de la pluralité de clients est un client suspect qui affiche un comportement dommageable dans la procédure FL, en effectuant un test avec un ensemble de données de référence, si au moins un client suspect est déterminé, pour exécuter une procédure d'identification afin d'identifier au moins un client malveillant, et pour effectuer un processus de mise à jour de modèle global en tenant compte d'un résultat d'une identification de client malveillant.