摘要
数据孤岛是制约人工智能技术发展和落地的主要障碍,随着国家与个人对隐私保护意识的增强,联邦学习在数据不共享的情况下,却能达到数据共享目的,受到广泛关注,联邦学习分为:横向联邦学习、纵向联邦学习和联邦迁移学习,具有数据隔离、质量保证、各参数方地位等同、独立性等优点,但联邦学习也存在很多的安全隐患,本文详细探讨了联邦学习的原理,提出了中央服务器、数据传输、单方数据污染、数据泄露以及对抗攻击等重要的数据安全问题,并汇总介绍了当前主要的防御措施。
Data island is the main obstacle that restricts the development and implementation of artificial intelligence technology.With the enhancement of the awareness of privacy protection of the state and individuals,federal learning can achieve the purpose of data sharing without data sharing,which has been widely concerned.Federal learning is divided into horizontal federal learning,vertical federal learning and federal transfer learning.It has the advantages of data isolation,quality assurance,equal status and independence of various parameters,but federal learning also has many security risks.This paper introduces the principle of federal learning in detail,some important data security problems such as central server,data transmission,unilateral data pollution,data leakage and anti-attack are put forward.Meanwhile,the current main defense measures are summarized.
作者
王壮壮
陈宏松
杨丽敏
陈丽芳
WANG Zhuangzhuang;CHEN Hongsong;YANG Limin;CHEN Lifang(College of Sciences,North China University of Science and Technology,Tangshan Hebei 063210,China)
出处
《智能计算机与应用》
2021年第1期126-129,133,共5页
Intelligent Computer and Applications
基金
河北省自然科学基金(F2014209086)。
关键词
联邦学习
数据安全
对抗攻击
数据投毒
federal learning
data security
anti-attack
data poisoning
