Data　Analysis　of　Network　Security　is　very　important　in　intrusion　detection　and　computer　forensics.　A　lot　of　data　mining　methods　to　research　it　have　been　found,　such　as　content-based　queries　and　similarity　searches　to　manage　and　use　such　data.　Fast　and　accurate　retrievals　for　content-based　queries　are　crucial　for　such　numerous　data　streams　to　be　useful.　In　this　paper,　we　apply　wavelet　transforms　into　network　security　to　analyze　and　mine　time-serial　data　streams　for　the　detection　of　anomalous　network　security　events.　We　first　proposes　a　wavelet　based　data　analysis　framework　for　network　security　traffic,　and　signalize　the　data　stream　of　network　security　(DSNS),　then　after　de-noise　of　DSNS,　we　use　wavelet　based　transforms　to　analyze　the　DSNS　and　get　anomalous　events　for　intrusion　detection　in　computer　network　security.　Experimental　results　show　that,　by　using　wavelet　transform,　we　can　decrease　the　noise　signal　and　keep　the　useful　signals　of　network　security　data　streams　to　retrieve　anomalous　events　effectively.