With　the　popularity　of　location　based　services,　spatial　keyword　query　has　become　an　important　application.　In　order　to　mininize　storage　and　computational　costs,　most　data　owners　will　outsource　the　data　to　the　cloud　server.　There　are,　however,　implications　such　as　potential　for　privacy　leakage　and　network　bandwidth　overheads.　To　solve　the　above　problems,　we　propose　a　Privacy-preserving　top-κ　Spatial　Keyword　queries　based　on　Fog　computing,　namely　PSKF.　To　further　improve　search　efficiency,　we　use　IR-tree　to　build　the　index　and　store　it　in　the　cloud　server.　Each　fog　server　also　saves　a　different　subtree　of　the　IR-tree,　so　that　we　can　decide　which　fog　server　to　participate　in　the　query　by　pruning.　Formal　security　analysis　shows　that　our　proposed　PSKF　achieves　Indistinguishability　under　Known-Plaintext　Attacks　(IND-KPA),　and　extensive　experiments　demonstrate　that　our　proposed　scheme　is　efficient　and　feasible　in　practical　applications.　©　2008-2012　IEEE.