Protecting　the　users＇　privacy　while　mining　information　from　massive　data　has　become　a　popular　research　topic　in　recent　years.　Perturbation　and　reconstruction　are　two　common　technologies　in　implementing　privacy　preserving　data　mining.　In　this　paper,　a　novel　perturbation　method　based　on　GM(1,1)　model　is　proposed　and　applied　to　data　clustering.　The　effectiveness　and　efficiency　of　the　proposed　method　is　demonstrated　by　the　experiments　on　real-world　datasets.　©　2011　IEEE.