In　this　paper,　we　propose　a　privacy-preserving　outsourced　calculation　toolkit,　Pockit,　designed　to　allow　data　owners　to　securely　outsource　their　data　to　the　cloud　for　storage.　The　outsourced　encrypted　data　can　be　processed　by　the　cloud　server　to　achieve　commonly-used　plaintext　arithmetic　operations　without　involving　additional　servers.　Specifically,　we　design　both　signed　and　unsigned　integer　circuits　using　a　fully　homomorphic　encryption　(FHE)　scheme,　construct　a　new　packing　technique　(hereafter　referred　to　as　integer　packing),　and　extend　the　secure　circuits　to　its　packed　version.　This　achieves　significant　improvements　in　performance　compared　with　the　original　secure　signed/unsigned　integer　circuit.　The　secure　integer　circuits　can　be　used　to　construct　a　new　data　mining　application,　which　we　refer　to　as　secure　$k$-nearest　neighbours　classifier,　without　compromising　the　privacy　of　original　data.　Finally,　we　prove　that　the　proposed　Pockit　achieves　the　goal　of　secure　computation　without　privacy　leakage　to　unauthorized　parties,　and　demonstrate　the　utility　and　efficiency　of　Pockit.　IEEE