Directional　modulation　(DM),　as　an　efficient　secure　transmission　method,　offers　security　through　its　directive　property　and　is　suitability　for　LoP　channels　such　as　millimeter　wave,　UAV,　satellite　communication,　and　smart　transportation.　If　the　direction　angle　of　the　desired　user　is　known,　the　desired　channel　gain　vector　is　obtainable.　Thus,　in　advance,　the　DM　transmitter　knows　the　values　of　the　directional　angles　of　the　desired　user　and　eavesdropper,　or　their　DOAs　because　the　BVCM　andANPM　are　mainly　determined　by　the　directional　angles　of　the　desired　user　and　eavesdropper.　For　a　DM　transceiver,　working　as　a　receiver,　the　first　step　is　to　measure　the　DOAs　of　the　desired　user　and　eavesdropper.　Then,　in　the　second　step,　using　the　measured　DOAs,　the　BVCM　and　ANPM　are　designed.　In　this　article,　we　describe　DOA　measurement　methods,　power　allocation,　and　beamforming　in　DM　networks.　A　machine　learning-based　DOA　measurement　method　is　proposed　to　make　a　substantial　secrecy　rate　(SR)　performance　gain　compared　to　single-snapshot　measurement　without　machine　learning　for　a　given　null-space　projection　beamforming　scheme.　However,　for　a　conventional　DM　network,　there　still　exists　a　serious　security　issue:　the　eavesdropper　moves　inside　the　main　beam　of　the　desired　user　and　may　intercept　the　CMs　intended　for　the　desired　users　because　the　BVCM　and　ANPM　are　only　angle-dependent.　To　address　this　problem,　we　present　a　new　concept　of　SPWT,　where　the　transmit　waveform　has　two-dimensional　dependency　by　using　DM,　random　subcarrier　selection　with　randomization　procedure,　and　phase　alignment　at　the　DM　transmitter.