|
Work item:
|
X.2212 (ex X.srm-fml)
|
|
Subject/title:
|
Security requirements and measures of federated machine learning
|
|
Status:
|
Determined on 2026-06-10 [Issued from previous study period]
|
|
Approval process:
|
TAP
|
|
Type of work item:
|
Recommendation
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
2026-Q2 (Medium priority)
|
|
Liaison:
|
ITU-T SG2, ITU-T SG16, ITU-T SG20, IEEE C/AISC/SPFML, IEEE C/AISC/FML
|
|
Supporting members:
|
China Information Communication Technologies Group, China Unicom, China Telecom
|
|
Summary:
|
Federated machine learning (FML) is a framework or system that enables multiple participants to collaboratively build and use machine learning models without disclosing the raw and private data, while still achieving good performance. In FML, original data cannot be transmitted to other clients or servers during the entire process; data usage only occurs where the data is stored. As a result, FML effectively addresses the problem of data silos and enables data sharing while ensuring privacy.
The typical stages of FML include data preparation, model training and model deployment. Although FML can protect local data privacy to a certain extent, it introduces new exploitable opportunities for attackers when model parameters are shared and models are aggregated. Since FML emphasizes distributed computing among different entities, there are many threats specific to FML compared with traditional machine learning (ML), such as free-riding attacks during the model training stage. These security risks and threats can seriously affect the functional correctness and data security of FML, limiting its application across various industries. At the same time, FML requires the use of appropriate security measures in advance to mitigate or defend against those risks and threats.
This Recommendation analyzes security risks and threats of FML and provides security requirements and measures that could mitigate or defend against the security risks and threats.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2024-03-11 12:37:12
|
|
Last update:
2026-06-26 11:51:26
|
