While　vehicle-to-everything　communication　technology　enables　information　sharing　and　cooperative　control　for　vehicles,　it　also　poses　a　significant　threat　to　the　vehicles＇　driving　security　owing　to　cyber-attacks.　In　particular,　Sybil　malicious　attacks　hidden　in　the　vehicle　broadcast　information　flow　are　challenging　to　detect,　thereby　becoming　an　urgent　issue　requiring　attention.　Several　researchers　have　considered　this　problem　and　proposed　different　detection　schemes.　However,　the　detection　performance　of　existing　schemes　based　on　plausibility　checks　and　neighboring　observers　is　affected　by　the　traffic　and　attacker　densities.　In　this　study,　we　propose　a　malicious　attack　detection　scheme　based　on　traffic-flow　information　fusion,　which　enables　the　detection　of　Sybil　attacks　without　neighboring　observer　nodes.　Our　solution　is　based　on　the　basic　safety　message,　which　is　broadcast　by　vehicles　periodically.　It　first　constructs　the　basic　features　of　traffic　flow　to　reflect　the　traffic　state,　subsequently　fuses　it　with　the　road　detector　information　to　add　the　road　fusion　features,　and　then　classifies　them　using　machine　learning　algorithms　to　identify　malicious　attacks.　The　experimental　results　demonstrate　that　our　scheme　achieves　the　detection　of　Sybil　attacks　with　an　accuracy　greater　than　90　%　at　different　traffic　and　attacker　densities.　Our　solutions　provide　security　for　achieving　a　usable　vehicle　communication　network.　©　2022　IFIP.