As　the　core　component　of　the　electronic　devices,　the　integrated　circuit　(IC)　must　be　taken　seriously　with　its　security.　The　pre-silicon　detection　methods　do　not　require　gold　chips,　are　not　affected　by　process　noise　and　are　suitable　for　the　safe　detection　of　a　very　large　scale　integration　(VLSI).　Therefore,　more　and　more　researchers　are　paying　attention　to　the　presilicon　detection　method.　In　this　paper,　we　propose　a　machine-learning-based　hardware-Trojans　detection　method　in　gatelevel.　First,　by　the　analysis　of　the　Trojan　circuits,　we　put　forward　new　Trojan-net　features.　After　that,　we　use　the　scoring　mechanism　of　the　eXtreme　Gradient　Boosting　(XGBoost)　to　set　up　a　new　effective　feature　set　of　49　out　of　56　features.　Finally,　the　hardware-Trojan　classifier　was　trained　based　on　the　effective　feature　set.　The　experimental　results　show　that　the　proposed　method　can　obtain　the　average　Recall　of　89.84%,　the　average　F-measure　of　87.75%　and　the　average　Accuracy　of　99.83%.　Furthermore,　through　the　comparison　experiments,　it　is　proved　that　the　features　proposed　in　this　paper　can　further　improve　the　performance　of　detection.