Malicious code within model detection method based on model similarity

Malicious code within model detection method based on model similarity

The privacy of user data in federated learning is mainly protected by exchanging model parameters instead of source data.However, federated learning still encounters many security challenges.Extensive research has been conducted to enhance model privacy and detect malicious model attacks.Nevertheles...

Full description

Saved in:
Bibliographic Details
Main Authors: Degang WANG, Yi SUN, Chuanxin ZHOU, Qi GAO, Fan YANG
Format: Article
Language:English
Published: POSTS&TELECOM PRESS Co., LTD 2023-08-01
Series:网络与信息安全学报
Subjects:
federated learning
model
model similarity
malicious code
detection
Online Access:http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2023056
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items