Network　devices　are　essential　to　connect　nodes　and　users　on　any　given　network.　Network　devices　perform　the　additional　task　of　protecting　services　and　users　from　known　and　unknown　attacks.　This　feature　of　network　devices　to　stop　or　minimize　network　attacks　to　secure　the　nodes　and　all　attached　devices　needs　further　research　studies　and　experimentation　to　confirm　their　resilience　against　potential　known　attacks.　Denial-of-Service　(DoS)　Attack　is　one　of　the　deadliest　attacks　that　make　network　services　and　devices　unavailable.　One　of　these　attacks,　which　is　growing　significantly,　is　the　Distributed　Denial　of　Service　(DDoS)　attack.　DDoS　attack　has　a　high　impact　on　crashing　the　network　resources,　making　the　target　servers　unable　to　support　valid　users.　The　current　methods　use　the　standard　datasets　to　deploy　the　Deep　Learning　(DL)　Model　for　intrusion　detection　against　DDoS　attacks　in　the　network.　However,　these　methods　suffer　several　drawbacks,　and　the　used　datasets　do　not　contain　the　most　recent　attack　patterns　–　henceforward,　lacking　in　attack　variety.　In　this　paper,　we　proposed　an　interruption　detection　model　system　and,　against　DDoS　attacks　is　based　on　DL　technique,　the　combination　of　the　Recurrent　Neural　Network　(RNN)　and　Deep　Neural　Network　(DNN)　algorithms　are　compared　with　an　autoencoder.　We　evaluated　our　DL　model　system　using　the　newly　released　dataset　CIC　DDoS2020,　which　contains　a　comprehensive　variety　of　DDoS　attacks　and　addresses　the　gaps　of　the　existing　current　datasets　(CIC　DDoS2020).　We　obtained　a　significant　improvement　in　attack　detection　compared　to　other　benchmarking　methods.　Hence,　our　model　provides　excellent　confidence　in　securing　these　networks.　©　(2023).　All　Rights　Reserved.