DNA　methylation　abnormalities　are　frequent　events　in　early　tumors.　DNA　methylation　is　relatively　stable　over　time　and　can　be　detected　in　blood.　Therefore,　DNA　methylation　has　a　great　potential　to　become　an　early　diagnostic　biomarker　of　cancers.　To　find　potential　diagnostic　markers　for　lung　squamous　cell　carcinoma　(LUSC),　a　method　for　identifying　LUSC-specific　candidate　diagnostic　markers　was　proposed.　We　screened　6　LUSC-specific　CpGs　by　comparing　the　methylation　profiles　of　172　samples　from　LUSC　patients,　42　normal　lung　samples,　1306　samples　from　patients　with　other　cancers,　which　was　collected　from　The　Cancer　Genome　Atlas　(TCGA)　database,　and　184　normal　blood　samples,　which　was　collected　from　Gene　Expression　Omnibus　(GEO)　database.　A　support　vector　machine　model　was　built　based　on　the　methylation　levels　of　the　candidate　diagnostic　biomarkers,　and　we　optimized　the　model　by　sixfold　cross-validation.　The　combination　of　six　sites　achieved　93%-99%　sensitivity　in　predicting　LUSC,　100%　specificity　in　excluding　normal　samples,　and　99.55%　specificity　in　excluding　non-LUSC　samples.　In　addition,　a　diagnostic　model　was　established　by　using　six　LUSC-specific　biomarkers,　and　the　sensitivity　and　specificity　of　LUSC　stage　I　samples　were　95.2%　and　99.4%.　At　the　same　time,　genes　for　six　LUSC-specific　CpGs　localization　are　closely　related　to　cancer　occurrence,　which　indicates　that　six　LUSC-specific　CpGs　can　be　used　as　candidate　biomarkers　for　LUSC　diagnosis.　Overall,　our　study　provides　promising　biomarkers　for　the　diagnosis　of　LUSC.