In　the　smart　grid,　the　Advanced　Metering　Infrastructure　(AMI)　will　be　deployed　to　monitor　and　control　the　power　grid　by　integrating　both　computing　and　networking　components　to　achieve　stable　and　efficient　operation.　The　AMI　is　vulnerable　to　cyber　attacks,　especially　in　the　form　of　data　integrity　attacks.　A　number　of　research　efforts　have　been　devoted　to　detecting　such　attacks.　Nonetheless,　the　majority　of　existing　schemes　either　rely　on　a　pre-defined　threshold,　or　require　external　knowledge.　This　leaves　open　the　possibility　for　low　detection　accuracy　when　the　threshold　is　improperly　defined,　and　where　there　is　a　lack　of　the　requisite　external　knowledge.　To　address　this　issue,　in　this　paper　we　propose　a　Gaussian-Mixture　Model-based　Detection　(GMMD)　scheme　to　combat　data　integrity　attacks.　Not　relying　upon　the　pre-defined　threshold　or　external　knowledge,　our　scheme　operates　by　narrowing　the　range　of　normal　data　that　can　be　obtained　by　clustering　the　historical　data　and　learning　the　minimum　and　maximum　values　of　individual　clusters.　To　validate　the　effectiveness　of　our　scheme,　we　conduct　performance　evaluation　based　on　the　Electricity　Load　Diagrams　2011　2014　data　set,　and　analyze　the　effectiveness　of　the　proposed　scheme　with　respect　to　detection　accuracy.　The　results　of　our　investigation　demonstrate　that　our　scheme　can　achieve　a　higher　detection　rate,　and　lower　error　rate,　in　comparison　with　existing　schemes　based　on　the　Min-Max　model.