简介：Duetodramaticallyincreasinginformationpublishedinsocialnetworks,privacyissueshavegivenrisetopublicconcerns.Althoughthepresenceofdifferentialprivacyprovidesprivacyprotectionwiththeoreticalfoundations,thetrade-offbetweenprivacyanddatautilitystilldemandsfurtherimprovement.However,mostexistingstudiesdonotconsiderthequantitativeimpactoftheadversarywhenmeasuringdatautility.Inthispaper,wefirstlyproposeapersonalizeddifferentialprivacymethodbasedonsocialdistance.Then,weanalyzethemaximumdatautilitywhenusersandadversariesareblindtothestrategysetsofeachother.Weformalizeallthepayofffunctionsinthedifferentialprivacysense,whichisfollowedbytheestablishmentofastaticBayesiangame.Thetrade-offiscalculatedbyderivingtheBayesianNashequilibriumwithamodifiedreinforcementlearningalgorithm.Theproposedmethodachievesfastconvergencebyreducingthecardinalityfromnto2.Inaddition,thein-placetrade-offcanmaximizetheuser'sdatautilityiftheactionsetsoftheuserandtheadversaryarepublicwhilethestrategysetsareunrevealed.Ourextensiveexperimentsonthereal-worlddatasetprovetheproposedmodeliseffectiveandfeasible.