Wi-fi　fingerprint-based　indoor　localization　is　regarded　as　one　of　the　most　promising　techniques　for　location-based　services.　Services　providers　would　like　to　train　the　localization　model　using　the　location　data.　Determining　how　to　protect　sensitive　information　in　the　indoor　localization　of　users　is　the　main　objective.　Dealing　with　the　problem　of　the　untrusted　third　party,　we　proposed　indoor　localization　mechanisms　based　on　local　differential　privacy.　It　extends　the　local　differential　privacy　theory　to　a　mature　machine-learning　localization　technology　to　achieve　privacy　protection　while　training　the　localization　model.　The　experiment　could　control　the　data　quality　loss　up　to　7.2%　compared　with　the　central　differential　privacy.　Our　investigation　suggests　that　it　could　provide　guidance　on　indoor　localization　privacy.　©　2023　IEEE.