聯(lián)邦學(xué)習(xí)中隱私保護(hù)聚合機(jī)制綜述

打開文本圖片集

Survey of privacy-preserving aggregation mechanisms in federated learning

Qiu Jiana，Ma Haiyinga?，Wang Zhanjun ，Shen Jinyua （a.SchoolofclecofUi China）

Abstract：Asanewdistributed machine learning（DML）framework，F(xiàn)Lcanefectively protectthelocaldata privacyof participantsbyaggregatingthelocalmodelparametersuploadedbyparticipantstotraintheglobalmodel.However，theselocal model parameters still have the risk of revealing the privacy of participants. As a critical step in FL ， the privacy-preserving aggregation （ PPAgg ）mechanism has become a key technology for addressing privacy issues.This paper first introduced the concept of FL and its associated privacyand security threats.It then highlighted the core ideas and key proceduresof PPAgg mechanisms by integrating existing privacy-preserving techniques inFL.This paper analyzed typical PPAgg mechanisms indetail，focsingontheirprimaryadvantagesandlimitations，aswellasthespecificapplicationscenarioswhereheyweresuitable.Finall，this papersummarized andanalyzed curent PPAgg mechanisms，explored emerging challenges anddevelopment directions for FL ，and proposed potential solutions to address these issues.

Key words：federated learning（FL）；privacy-preserving；aggregation mechanism；blockchain；securemulti-partycomputation

0 引言

機(jī)器學(xué)習(xí)（ML）作為實(shí)現(xiàn)人工智能的一種重要手段，利用收集的原始數(shù)據(jù)訓(xùn)練特定場(chǎng)景下的數(shù)據(jù)模型，以達(dá)到使機(jī)器模擬人類行為的目標(biāo)。（剩余30283字）